@agent-native/core 0.27.0 → 0.28.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -33,14 +33,14 @@ component in dev and prod.
33
33
  - Reads `application_state.navigation` every turn, so it already knows which
34
34
  view you're in and what's selected — you don't have to re-explain "this".
35
35
 
36
- ### Dev vs prod tool modes {#tool-modes}
36
+ ### App vs Code tool modes {#tool-modes}
37
37
 
38
38
  The panel runs in one of two tool modes:
39
39
 
40
- - **Production mode** — the agent only has your app's own tools: the actions you
40
+ - **App mode** — the agent only has your app's own tools: the actions you
41
41
  defined with `defineAction`, plus navigation and context. No filesystem or
42
42
  shell access. This is what end users get.
43
- - **Development mode** — adds the shared coding tools (`bash`, `read`, `edit`,
43
+ - **Code mode** — adds the shared coding tools (`bash`, `read`, `edit`,
44
44
  `write`) and database access on top of the app tools, so the agent can change
45
45
  the app's own source. Code requests are gated: when a message requires code
46
46
  (`type: "code"`) and no code-capable frame is connected, the panel shows a
@@ -48,9 +48,15 @@ The panel runs in one of two tool modes:
48
48
  when a frame is connected, the request is routed to it and a code-agent
49
49
  indicator shows while it works (`useSendToAgentChat`).
50
50
 
51
+ "Code mode" is the agent-capability toggle — distinct from environment dev mode
52
+ (`NODE_ENV` / Vite). For back-compat the underlying `AGENT_MODE` env var, the
53
+ `/_agent-native/agent-chat/mode` endpoint (whose payload still uses `devMode`),
54
+ and the `agent-chat.mode` settings key are unchanged. The client hook is
55
+ `useCodeMode()` (the older `useDevMode()` remains as a deprecated alias).
56
+
51
57
  In the local dev frame, the settings cog toggles between these modes. Switching
52
- to prod hides the frame's own sidebar and shows the app's in-app agent sidebar
53
- inside the iframe instead, so you can preview exactly what end users see.
58
+ off Code mode hides the frame's own sidebar and shows the app's in-app agent
59
+ sidebar inside the iframe instead, so you can preview exactly what end users see.
54
60
 
55
61
  ## Integrated terminal and CLI switching {#cli-terminal}
56
62
 
@@ -139,7 +139,7 @@ Change how the agent behaves, in 60 seconds.
139
139
 
140
140
  ## How the Agent Uses Resources {#how-the-agent-uses-resources}
141
141
 
142
- The agent has built-in tools for managing resources: `resource-list`, `resource-read`, `resource-effective`, `resource-write`, and `resource-delete`. These are available in both dev and production modes.
142
+ The agent has built-in tools for managing resources: `resource-list`, `resource-read`, `resource-effective`, `resource-write`, and `resource-delete`. These are available in both Code mode and App mode.
143
143
 
144
144
  At the start of every conversation, the agent automatically reads:
145
145
 
@@ -337,8 +337,8 @@ When the agent encounters a task that matches a skill, it reads the skill file a
337
337
 
338
338
  There are two ways to add skills:
339
339
 
340
- 1. **Via Workspace tab** — Create a new resource with a path like `skills/my-skill/SKILL.md`. This works in both dev and production.
341
- 2. **Via code (dev only)** — Add a Markdown file to `.agents/skills/` in your project. These are available when the app runs in dev mode.
340
+ 1. **Via Workspace tab** — Create a new resource with a path like `skills/my-skill/SKILL.md`. This works in both Code mode and App mode.
341
+ 2. **Via code (Code mode only)** — Add a Markdown file to `.agents/skills/` in your project. These are available when the app runs in Code mode.
342
342
 
343
343
  ## Custom Agents {#custom-agents}
344
344
 
@@ -435,8 +435,8 @@ When you send a message:
435
435
 
436
436
  What shows up depends on the mode:
437
437
 
438
- - **Dev mode** — Codebase files, workspace resources, custom agents, and connected agents
439
- - **Production mode** — Workspace resources, custom agents, and connected agents
438
+ - **Code mode** — Codebase files, workspace resources, custom agents, and connected agents
439
+ - **App mode** — Workspace resources, custom agents, and connected agents
440
440
 
441
441
  ## / Slash Commands {#slash-commands}
442
442
 
@@ -444,16 +444,16 @@ Type `/` at the start of a line to invoke a skill. A dropdown shows available sk
444
444
 
445
445
  What shows up depends on the mode:
446
446
 
447
- - **Dev mode** — Skills from `.agents/skills/` (codebase) and skills from resources
448
- - **Production mode** — Skills from resources only
447
+ - **Code mode** — Skills from `.agents/skills/` (codebase) and skills from resources
448
+ - **App mode** — Skills from resources only
449
449
 
450
450
  If no skills are configured, the dropdown shows a hint with a link to these docs.
451
451
 
452
- ## Dev vs Production Mode {#dev-vs-prod}
452
+ ## Code vs App Mode {#dev-vs-prod}
453
453
 
454
454
  The resource system works identically in both modes. The difference is what additional sources are available for `@` tagging and `/` commands:
455
455
 
456
- | Feature | Dev Mode | Production |
456
+ | Feature | Code Mode | App Mode |
457
457
  | ------------------ | ----------------------------------------------------------------------- | ------------------------------------------------------ |
458
458
  | @ tagging | Codebase files + workspace resources + custom agents + connected agents | Workspace resources + custom agents + connected agents |
459
459
  | / slash commands | .agents/skills/ + resource skills | Resource skills only |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@agent-native/core",
3
- "version": "0.27.0",
3
+ "version": "0.28.0",
4
4
  "type": "module",
5
5
  "engines": {
6
6
  "node": ">=22"