@hybridaione/hybridclaw 0.12.2 → 0.12.4

package/CHANGELOG.md

@@ -2,6 +2,106 @@
 
 ## [Coming up]
 
+## [0.12.4](https://github.com/HybridAIOne/hybridclaw/tree/v0.12.4)
+
+### Added
+
+- **Slack channel transport**: Added a built-in Slack Socket Mode transport
+  with `hybridclaw auth login slack`, DM and channel policy controls,
+  thread-aware session routing, file/media handling, approval buttons, and a
+  dedicated setup guide for operator rollout.
+- **Immediate one-shot scheduler jobs**: Added config-backed `one_shot` jobs
+  that run immediately, retry up to `maxRetries`, preserve review state, and
+  surface richer delivery output across the gateway and admin scheduler UI.
+
+### Changed
+
+- **Admin console dialog and toast UX**: Replaced inline banners with
+  accessible dialog/toast primitives, tightened scheduler and jobs feedback
+  flows, and refined the mobile topbar/sidebar interaction.
+- **Per-agent skill filtering**: Agent `skills` settings now narrow the
+  globally enabled skill set, while omitting `skills` keeps the existing
+  global scope for backward compatibility.
+- **Approval presentation across channels**: Gateway approval copy and channel
+  actions now render more consistently, preserve approval ids correctly, and
+  align Discord and Slack approval flows more closely.
+
+### Fixed
+
+- **Slack slash-command ergonomics**: Slack slash commands use shorter
+  `/hc-*` names, keep runtime command coverage aligned with the shipped
+  manifest, and avoid review regressions in channel setup/documentation flows.
+- **Scheduler delivery state reporting**: One-shot deliveries now report retry
+  and review outcomes more clearly instead of leaving ambiguous scheduler state
+  after gateway or console handoff.
+- **Console accessibility edge cases**: Toast and dialog flows now keep
+  backdrops interactive, ignore closed dialogs in Escape-key handling, and
+  harden focus/visibility coordination during layered UI interactions.
+
+## [0.12.3](https://github.com/HybridAIOne/hybridclaw/tree/v0.12.3)
+
+### Added
+
+- **Telegram Bot API transport**: Added a built-in Telegram channel with
+  BotFather token setup, DM/group policy controls, admin Channels support,
+  managed `TELEGRAM_BOT_TOKEN` storage, inbound media handling, and canonical
+  outbound `telegram:<chatId>` send targets.
+- **Built-in memory inspection command**: Added local `/memory inspect
+  [sessionId]`, `/memory query <query>`, and `hybridclaw gateway memory inspect
+  [sessionId]` diagnostics to show `MEMORY.md`, today's daily note, recent raw
+  history, `session_summary`, recent semantic-memory rows, canonical
+  cross-session recall state, and the exact prompt-memory block the current
+  session would attach for a query.
+- **Admin email mailbox surfaces**: Added admin-console and gateway support for
+  browsing the configured built-in email mailbox, listing folders and message
+  metadata, and composing or replying from the operator UI without leaving the
+  HybridClaw runtime.
+- **Native LOCOMO eval workflow**: Added managed `hybridclaw eval locomo ...`
+  and local `/eval locomo ...` flows with official dataset setup, QA and
+  retrieval modes, detached run logs, and retrieval sweeps across backend,
+  rerank, tokenizer, and embedding settings.
+- **Bundled GBrain plugin**: Added the bundled `gbrain` plugin so HybridClaw
+  can query an external GBrain knowledge brain for prompt-time recall, expose
+  discovered `gbrain_*` tools, and provide `/gbrain ...` passthrough operations
+  from local sessions.
+- **Bundled manim-video skill**: Added a repo-shipped `manim-video` skill with
+  setup helpers, reference packs, and render guidance for scripted explainer
+  videos and animation workflows.
+
+### Changed
+
+- **Model catalog and provider routing**: `/model list` plus selector surfaces
+  now use provider-scoped model catalogs for Codex, OpenRouter, Mistral, and
+  Hugging Face, Codex models use explicit `openai-codex/...` ids, and status
+  output carries discovered model metadata more consistently.
+- **Admin console navigation and channel UX**: The embedded console now uses a
+  structured sidebar taxonomy, a clearer channel catalog, richer channel/email
+  surfaces, and refreshed icons/layout so operators can reach models, channels,
+  plugins, tools, and gateway state from one navigation frame.
+- **Shared inbound media cache**: Email, Telegram, WhatsApp, and Microsoft
+  Teams now stage locally downloaded inbound media under the shared
+  `uploaded-media-cache` runtime directory instead of per-channel temp
+  folders, aligning cleanup and runtime-safe media paths across those
+  transports.
+- **Telegram config reload behavior**: Running gateways now restart the
+  Telegram integration automatically when `telegram.*` config changes land, so
+  most setup edits apply within a few seconds without a full gateway restart.
+- **Per-agent skill allowlists**: Agent `skills` settings now narrow the
+  globally enabled skill set, while omitting `skills` keeps the existing
+  globally enabled scope for backward compatibility.
+
+### Fixed
+
+- **TUI sandbox preflight**: `hybridclaw tui` now follows the sandbox mode
+  reported by a reachable gateway, avoiding unnecessary container rebuild
+  checks when the running gateway is already in host mode and vice versa.
+- **HybridAI auxiliary model prefixes**: Auxiliary-model routing now strips the
+  leading provider prefix correctly so HybridAI requests do not fail when the
+  configured model name already carries a provider namespace.
+- **GBrain tool discovery robustness**: The bundled GBrain plugin now times out
+  cleanly when `gbrain --tools-json` hangs and reports parse failures with
+  stdout/stderr previews during discovery.
+
 ## [0.12.2](https://github.com/HybridAIOne/hybridclaw/tree/v0.12.2)
 
 ### Added

package/README.md

@@ -9,21 +9,29 @@
 [![Powered by HybridAI](https://img.shields.io/badge/powered%20by-HybridAI-blueviolet)](https://hybridai.one)
 [![Discord](https://img.shields.io/badge/Discord-join%20chat-5865F2?logo=discord&logoColor=white)](https://discord.gg/jsVW4vJw27)
 
-<img width="420" height="397" alt="HybridClaw - The enterprise operating layer for open agents" src="docs/hero.png" />
+<img width="420" height="397" alt="HybridClaw - Enterprise-ready self-hosted AI assistant runtime" src="docs/hero.png" />
 
 ## All of the Claw, None of the Chaos
-### Your enterprise operating layer for open agents
+### Enterprise-ready self-hosted AI assistant runtime
 
-Self-hosted, controllable, and built for real business workflows.
+HybridClaw is a self-hosted AI assistant runtime for teams that need control,
+security, and operational visibility. It combines sandboxed execution, secure
+credentials, approvals, persistent memory, and admin surfaces behind a single
+gateway.
 
-Most open agent stacks are optimized for experimentation and breadth.
+Connect it to Discord, Slack, WhatsApp, Telegram, Microsoft Teams, email, or the web. Run it
+locally, deploy it for business workflows, and keep your agents, secrets, and
+data under your control.
 
-HybridClaw is optimized for enterprise deployment:
-- controlled execution
-- shared knowledge
-- observability
-- repeatable enterprise workflows
-- local-first deployment
+## Coming from OpenClaw or Hermes?
+
+```bash
+hybridclaw migrate openclaw --dry-run
+hybridclaw migrate hermes --dry-run
+```
+
+Preview and import compatible state from OpenClaw or Hermes in minutes.
+Imports compatible skills, memory, config, and optional secrets.
 
 ## HybridAI Platform Advantage
 
@@ -60,16 +68,6 @@ Release notes live in [CHANGELOG.md](./CHANGELOG.md), and the browsable
 operator and maintainer manual lives at
 [hybridclaw.io/docs](https://www.hybridclaw.io/docs/).
 
-## Coming from OpenClaw or Hermes?
-
-```bash
-hybridclaw migrate openclaw --dry-run
-hybridclaw migrate hermes --dry-run
-```
-
-Preview and import compatible state from OpenClaw or Hermes in minutes.
-Imports compatible skills, memory, config, and optional secrets.
-
 ## See it in Action
 
 Once the gateway is running, open HybridClaw locally:
@@ -77,7 +75,7 @@ Once the gateway is running, open HybridClaw locally:
 - Web Chat: `http://127.0.0.1:9090/chat`
 - Admin Console: `http://127.0.0.1:9090/admin` for channels, scheduler, audit, and config
 - Agent Dashboard: `http://127.0.0.1:9090/agents`
-- or connect Whatsapp, Discord, MS Teams, Email
+- or connect Slack, WhatsApp, Telegram, Discord, Microsoft Teams, Email
 
 ## How HybridClaw compares
 
@@ -101,9 +99,10 @@ Once the gateway is running, open HybridClaw locally:
 | Workflow builder vs agent runtime | Agent runtime | Framework for building agent systems | Visual workflow builder |
 | Enterprise controls | ✅ Approvals, audit, sandbox, encrypted secrets | ⚠️ You build them | ⚠️ Workflow-level controls |
 
-## Built for enterprise operations
+## Security and governance built in
 
-- encrypted secrets
+- secure credential storage
+- sandboxed execution
 - approvals
 - audit trails with hash chain
 - config versioning and backup/rollback
@@ -125,7 +124,7 @@ Once the gateway is running, open HybridClaw locally:
 
 ## Architecture
 
-- **Gateway service** (Node.js) — shared message/command handlers, SQLite persistence (KV + semantic + knowledge graph + canonical sessions + usage events), scheduler, heartbeat, web/API, loopback OpenAI-compatible API, and channel integrations for Discord, Microsoft Teams, iMessage, WhatsApp, and email
+- **Gateway service** (Node.js) — shared message/command handlers, SQLite persistence (KV + semantic + knowledge graph + canonical sessions + usage events), scheduler, heartbeat, web/API, loopback OpenAI-compatible API, and channel integrations for Discord, Slack, Microsoft Teams, Telegram, iMessage, WhatsApp, and email
 - **TUI client** — thin client over HTTP (`/api/chat`, `/api/command`) with
   a structured startup banner that surfaces model, sandbox, gateway, and
   chatbot context before the first prompt
@@ -138,35 +137,37 @@ Browse the full manual at
 [hybridclaw.io/docs](https://www.hybridclaw.io/docs/).
 
 - Getting started:
-  [Installation](https://www.hybridclaw.io/docs/development/getting-started/installation),
-  [Authentication](https://www.hybridclaw.io/docs/development/getting-started/authentication), and
-  [Quick Start](https://www.hybridclaw.io/docs/development/getting-started/quickstart)
+  [Installation](https://www.hybridclaw.io/docs/getting-started/installation),
+  [Authentication](https://www.hybridclaw.io/docs/getting-started/authentication), and
+  [Quick Start](https://www.hybridclaw.io/docs/getting-started/quickstart)
 - Enterprise deployment:
-  [Runtime Internals](https://www.hybridclaw.io/docs/development/internals/runtime) and
-  [Architecture](https://www.hybridclaw.io/docs/development/internals/architecture)
+  [Runtime Internals](https://www.hybridclaw.io/docs/internals/runtime) and
+  [Architecture](https://www.hybridclaw.io/docs/internals/architecture)
 - Operations:
-  [Remote Access](https://www.hybridclaw.io/docs/development/guides/remote-access)
+  [Remote Access](https://www.hybridclaw.io/docs/guides/remote-access)
 - Security:
   [SECURITY.md](./SECURITY.md) and [TRUST_MODEL.md](./TRUST_MODEL.md)
 - Migration:
-  [Commands: Migration](https://www.hybridclaw.io/docs/development/reference/commands#migration) and
-  [FAQ](https://www.hybridclaw.io/docs/development/reference/faq#can-i-migrate-an-existing-openclaw-or-hermes-agent-home)
+  [Commands: Migration](https://www.hybridclaw.io/docs/reference/commands#migration) and
+  [FAQ](https://www.hybridclaw.io/docs/reference/faq#can-i-migrate-an-existing-openclaw-or-hermes-agent-home)
 - Channels:
-  [Channel Setup](https://www.hybridclaw.io/docs/development/getting-started/channels),
+  [Channel Setup](https://www.hybridclaw.io/docs/getting-started/channels),
+  [Slack](https://www.hybridclaw.io/docs/slack),
   [iMessage](https://www.hybridclaw.io/docs/imessage), and
   [MS Teams](https://www.hybridclaw.io/docs/msteams)
 - Skills and plugins:
-  [Extensibility](https://www.hybridclaw.io/docs/development/extensibility),
-  [Bundled Skills](https://www.hybridclaw.io/docs/development/guides/bundled-skills),
-  [Plugin System](https://www.hybridclaw.io/docs/development/extensibility/plugins),
-  [Honcho Memory Plugin](https://www.hybridclaw.io/docs/development/extensibility/honcho-memory-plugin), and
-  [MemPalace Memory Plugin](https://www.hybridclaw.io/docs/development/extensibility/mempalace-memory-plugin)
+  [Extensibility](https://www.hybridclaw.io/docs/extensibility),
+  [Bundled Skills](https://www.hybridclaw.io/docs/guides/bundled-skills),
+  [Plugin System](https://www.hybridclaw.io/docs/extensibility/plugins),
+  [GBrain Plugin](https://www.hybridclaw.io/docs/extensibility/gbrain-plugin),
+  [Honcho Memory Plugin](https://www.hybridclaw.io/docs/extensibility/honcho-memory-plugin), and
+  [MemPalace Memory Plugin](https://www.hybridclaw.io/docs/extensibility/mempalace-memory-plugin)
 - Configuration:
-  [Configuration Reference](https://www.hybridclaw.io/docs/development/reference/configuration)
+  [Configuration Reference](https://www.hybridclaw.io/docs/reference/configuration)
 - CLI reference:
-  [Commands](https://www.hybridclaw.io/docs/development/reference/commands),
-  [Diagnostics](https://www.hybridclaw.io/docs/development/reference/diagnostics), and
-  [FAQ](https://www.hybridclaw.io/docs/development/reference/faq)
+  [Commands](https://www.hybridclaw.io/docs/reference/commands),
+  [Diagnostics](https://www.hybridclaw.io/docs/reference/diagnostics), and
+  [FAQ](https://www.hybridclaw.io/docs/reference/faq)
 
 ## Contributing
 

package/config.example.json

@@ -1,5 +1,5 @@
 {
-  "version": 18,
+  "version": 21,
   "security": {
     "trustModelAccepted": false,
     "trustModelAcceptedAt": "",
@@ -12,6 +12,8 @@
     "channelDisabled": {
       "discord": [],
       "msteams": [],
+      "slack": [],
+      "telegram": [],
       "whatsapp": [],
       "email": []
     }
@@ -121,6 +123,29 @@
       "teams.microsoft.com"
     ]
   },
+  "slack": {
+    "enabled": false,
+    "groupPolicy": "allowlist",
+    "dmPolicy": "allowlist",
+    "allowFrom": [],
+    "groupAllowFrom": [],
+    "requireMention": true,
+    "textChunkLimit": 12000,
+    "replyStyle": "thread",
+    "mediaMaxMb": 20
+  },
+  "telegram": {
+    "enabled": false,
+    "botToken": "",
+    "pollIntervalMs": 1500,
+    "dmPolicy": "allowlist",
+    "groupPolicy": "disabled",
+    "allowFrom": [],
+    "groupAllowFrom": [],
+    "requireMention": true,
+    "textChunkLimit": 4000,
+    "mediaMaxMb": 20
+  },
   "whatsapp": {
     "dmPolicy": "pairing",
     "groupPolicy": "disabled",
@@ -174,17 +199,7 @@
     "models": ["gpt-4.1-mini", "gpt-5-nano", "gpt-5"]
   },
   "codex": {
-    "baseUrl": "https://chatgpt.com/backend-api/codex",
-    "models": [
-      "openai-codex/gpt-5-codex",
-      "openai-codex/gpt-5.3-codex",
-      "openai-codex/gpt-5.4",
-      "openai-codex/gpt-5.3-codex-spark",
-      "openai-codex/gpt-5.2-codex",
-      "openai-codex/gpt-5.1-codex-max",
-      "openai-codex/gpt-5.2",
-      "openai-codex/gpt-5.1-codex-mini"
-    ]
+    "baseUrl": "https://chatgpt.com/backend-api/codex"
   },
   "openrouter": {
     "enabled": false,
@@ -353,7 +368,19 @@
   },
   "memory": {
     "decayRate": 0.1,
-    "consolidationIntervalHours": 24
+    "consolidationIntervalHours": 24,
+    "consolidationLanguage": "en",
+    "semanticPromptHardCap": 12,
+    "embedding": {
+      "provider": "hashed",
+      "model": "onnx-community/embeddinggemma-300m-ONNX",
+      "revision": "75a84c732f1884df76bec365346230e32f582c82",
+      "dtype": "q8"
+    },
+    "queryMode": "no-stopwords",
+    "backend": "hybrid",
+    "rerank": "bm25",
+    "tokenizer": "porter"
   },
   "sessionRouting": {
     "dmScope": "per-channel-peer",