@agent-native/core 0.35.2 → 0.36.0

package/src/templates/default/DEVELOPING.md

@@ -81,7 +81,7 @@ export default defineNitroPlugin(async (nitroApp) => {
 | `readResource`, `writeResource`              | Read/write resources (from `@agent-native/core/resources`)                 |
 | `defineEventHandler`, `readBody`, `getQuery` | H3 route handler utilities (re-exported)                                   |
 | `sendToAgentChat`                            | Send or prefill messages in the agent chat from UI (client-side)           |
-| `setContextToAgentChat`                      | Stage keyed context chips for the next agent chat prompt from UI           |
+| Agent chat context state helpers             | Optional advanced helpers for two-way sync with staged context chips       |
 | `agentChat`                                  | Send messages to agent from scripts (server-side)                          |
 
 ## Adding a Script
@@ -102,18 +102,12 @@ sendToAgentChat({
 });
 ```
 
-To add hidden context without submitting or filling the prompt text, stage
-keyed context nuggets. Multiple nuggets stack; using the same `key` replaces the
-previous nugget.
-
-```ts
-import { setContextToAgentChat } from "@agent-native/core";
-setContextToAgentChat({
-  key: "selected-record",
-  title: "Selected Record",
-  context: JSON.stringify(record, null, 2),
-});
-```
+For most UI handoffs, pass hidden context directly with `sendToAgentChat()`. Use
+`submit: false` when the user should review the draft first. Use
+`useAgentChatContext`, `setAgentChatContextItem`, `listAgentChatContext`,
+`removeAgentChatContextItem`, and `clearAgentChatContext` only for advanced UI
+that needs to read, mirror, stage, remove, or clear staged context chips as local
+interface state.
 
 **From scripts:**
 

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

@@ -14,10 +14,12 @@ agent should know.
 - All AI/LLM behavior goes through the app's agent chat. UI and server code
   must not call model providers, AI SDK `generateText()` / `streamText()`, or
   other inline LLM APIs directly. Use `sendToAgentChat()` for local app-agent
-  work. When selected UI data should become hidden context for the user's next
-  prompt without submitting anything, use `setContextToAgentChat()` with a
-  stable `key`. Read `.agents/skills/delegate-to-agent/SKILL.md` before
-  building agent-driven UI or "AI" features.
+  work, including hidden `context` and `submit: false` prefill/review flows.
+  Only use `useAgentChatContext`, `setAgentChatContextItem`,
+  `listAgentChatContext`, `removeAgentChatContextItem`, and
+  `clearAgentChatContext` when UI needs two-way sync with staged context chips.
+  Read `.agents/skills/delegate-to-agent/SKILL.md` before building agent-driven
+  UI or "AI" features.
 - Put shared code in `packages/shared` only when multiple apps need it.
 - Keep app-specific screens, actions, state, and skills inside `apps/<app>`.
 - Store shared runtime configuration in the workspace root `.env`; use

package/src/templates/workspace-root/AGENTS.md

@@ -11,10 +11,12 @@ coding agents can discover the same workspace-wide guidance from the root.
 - All AI/LLM behavior goes through the app's agent chat. UI and server code
   must not call model providers, AI SDK `generateText()` / `streamText()`, or
   other inline LLM APIs directly. Use `sendToAgentChat()` for local app-agent
-  work. When selected UI data should become hidden context for the user's next
-  prompt without submitting anything, use `setContextToAgentChat()` with a
-  stable `key`. Read `packages/shared/.agents/skills/delegate-to-agent/SKILL.md`
-  before building agent-driven UI or "AI" features.
+  work, including hidden `context` and `submit: false` prefill/review flows.
+  Only use `useAgentChatContext`, `setAgentChatContextItem`,
+  `listAgentChatContext`, `removeAgentChatContextItem`, and
+  `clearAgentChatContext` when UI needs two-way sync with staged context chips.
+  Read `packages/shared/.agents/skills/delegate-to-agent/SKILL.md` before
+  building agent-driven UI or "AI" features.
 
 ## Workspace Resources