@agent-native/core 0.149.2 → 0.149.3

package/dist/templates/workspace-core/.agents/skills/writing-agent-instructions/SKILL.md

@@ -43,9 +43,9 @@ A template `AGENTS.md` is injected into the runtime agent's system prompt and
 hard-sliced at `COMPACT_PROMPT_RESOURCE_MAX_CHARS` (6,000). Past that, the agent
 sees a truncation marker instead of your text, so the tail stops being
 always-on guidance and becomes something it has to go fetch. `pnpm
-the repository's `guard:agent-chat-context` check fails the build when a first-party
-file overflows; generated apps do not ship that repository-only guard. Keep files
-under ~5,500 so ordinary edits don't tip them over.
+guard:agent-chat-context` — the repository's own check — fails the build when a
+first-party file overflows; generated apps do not ship that repository-only
+guard. Keep files under ~5,500 so ordinary edits don't tip them over.
 
 Two consequences worth designing around:
 

package/dist/templates/workspace-core/AGENTS.md

@@ -31,25 +31,18 @@ agent should know.
 
 - All AI/LLM behavior goes through the app's agent chat. UI and server code must
   not call model providers or AI SDK `generateText()` / `streamText()` directly;
-  use `sendToAgentChat()`. Keep actions deterministic and focused. If a
-  workflow is framed as research, analysis, generation, recommendation, or
-  synthesis, use `sendToAgentChat({ openSidebar: true })` to open the
-  AgentSidebar and let the agent orchestrate its provider/data actions. Keep
-  follow-ups in the same thread, not a second freeform textbox. Read
-  `.agents/skills/delegate-to-agent/SKILL.md` before building agent-driven UI or
-  "AI" features.
+  use `sendToAgentChat()`. Keep actions deterministic and focused. Research,
+  analysis, generation, recommendation, and synthesis open the AgentSidebar with
+  `sendToAgentChat({ openSidebar: true })` and stay in the same thread — never a
+  second freeform textbox. Read `delegate-to-agent` first.
 - Keep domain workflows on named routes and preserve the scaffold's full-page
-  chat route. Use the right `AgentSidebar` for contextual AI and open it when a
-  domain button hands work to the agent.
+  chat route.
 - Keep the first viewport focused: one primary action, progressive disclosure,
   concise copy, and domain-specific navigation. Never use sparkle, wand,
   magic, or robot icons as AI affordances.
 - Data loads use layout-matching `Skeleton` geometry, never a
   generic "Loading..." label. Reserve `Spinner` for brief mutations, uploads,
   and progress actions.
-- Use a sans-first SaaS hierarchy with one restrained visual cue; reserve serif
-  type for content previews. Give the AgentSidebar a subtle surface/divider
-  boundary, and stack original/generated review vertically by default.
 - Before visual work, read `frontend-design` and the workspace/app `DESIGN.md`.
   Keep shared chrome semantic and neutral, then choose an app-specific visual
   direction and palette family instead of copying a sibling app by default.
@@ -90,10 +83,8 @@ first-party template patterns ship with `@agent-native/core`. From an app
 directory, use `pnpm action docs-search --query "<topic>"` and
 `pnpm action source-search --query "<pattern>"`. Read `workspace-conventions`
 for slugs, the `--list` / `--slug` / `--path` options, and the `rg` fallback.
-
-Use package docs for framework APIs, the package corpus for reusable
-framework/template patterns, and this `AGENTS.md` plus `.agents/skills/` for
-workspace-specific conventions.
+Use package docs for framework APIs, the corpus for reusable patterns, and this
+file plus `.agents/skills/` for workspace-specific conventions.
 
 ## Actions
 

package/docs/content/messaging.mdx

@@ -124,8 +124,7 @@ Slack workspace, app, channel, and thread IDs are part of the conversation key.
    ```
 
 4. Turn on **Event Subscriptions**, set the **Request URL**, and subscribe to
-   `app_home_opened`, `app_context_changed`, `app_mention`, `message.channels`,
-   `message.groups`, `message.im`, and `message.mpim`:
+   `app_home_opened`, `app_context_changed`, `app_mention`, and `message.im`:
 
    ```text
    https://your-app.example.com/_agent-native/integrations/slack/webhook
@@ -171,10 +170,10 @@ take precedence.
 
 ### Slack-native collaboration
 
-- **Active thread steering.** Start in a channel with an `@mention`. While that
-  exact task is queued or running, ordinary replies in its Slack thread continue
-  the task without another mention. Inactive threads and general channel chatter
-  do not invoke the agent. DMs remain direct invocations.
+- **Explicit thread turns.** Start in a channel with an `@mention`. Each later
+  channel turn must explicitly mention the agent too. Ordinary thread replies,
+  inactive threads, and general channel chatter do not invoke it. DMs remain
+  direct invocations.
 - **Bounded native context.** Before execution, the adapter loads a bounded
   slice of the Slack thread plus channel, sender, reaction, and file metadata.
   It keeps file references and permalinks, never raw file bodies, in durable
@@ -228,7 +227,7 @@ and `link_shared` events to the Clips unfurl handler.
 
 ### Tips
 
-- **Channel mentions** — use an @mention to start work. Unmentioned replies are accepted only while that exact thread has active work.
+- **Channel mentions** — use an @mention to start work. Each channel turn must explicitly mention the agent; ordinary thread replies and general channel chatter do not invoke it.
 - **DMs** — accepted personal DMs are private conversations and require a verified organization member or linked Slack identity.
 - **Identity** — personal DMs require a verified Agent Native organization member or an already linked Slack identity. Configured channels use a separate service principal, policy, and budget.
 - **Production allowlists** — set `SLACK_ALLOWED_TEAM_IDS` and, for shared Slack apps, `SLACK_ALLOWED_API_APP_IDS` so a valid signing secret cannot be reused by an unexpected workspace.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agent-native/core",
-  "version": "0.149.2",
+  "version": "0.149.3",
   "description": "Framework for agent-native application development — where AI agents and UI share SQL state, actions, and context",
   "homepage": "https://github.com/BuilderIO/agent-native#readme",
   "bugs": {