@ai4b-team/fsaos-gateway-sdk 3.42.0 → 4.0.0
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.
- package/README.md +9 -9
- package/dist/iife/gateway.js +4 -4
- package/dist/iife/gateway.js.map +3 -3
- package/dist/iife/ui.js +1 -1
- package/dist/index.cjs +13 -2
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +21 -3
- package/dist/index.d.ts +21 -3
- package/dist/index.js +13 -3
- package/dist/index.js.map +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -76,23 +76,23 @@ Plain HTML can use the same contract without loading the SDK:
|
|
|
76
76
|
### Query Key Factory
|
|
77
77
|
- `vfsKeys` — Deterministic query keys for all VFS data
|
|
78
78
|
|
|
79
|
-
### Channel
|
|
79
|
+
### Channel Room Modes
|
|
80
80
|
|
|
81
|
-
Channels contain principals as members. AI is represented as a principal/member, not as a separate channel type. The SDK exposes
|
|
81
|
+
Channels contain principals as members. AI is represented as a principal/member, not as a separate channel type. The SDK exposes the room mode through `Channel.aiMode` (Agent System Master Spec D17; kernel revision `b7c4d2a9e1f3`, 2026-10-29):
|
|
82
82
|
|
|
83
83
|
| `Channel.aiMode` | Meaning |
|
|
84
84
|
|------------------|---------|
|
|
85
|
-
| `"
|
|
86
|
-
| `"
|
|
85
|
+
| `"open"` | The floor decision runs on every message; whoever it names answers. |
|
|
86
|
+
| `"active"` | Only the on-duty agents answer a person (`Channel.activeAgentIds`; absent = every agent seated in the channel). An agent's message wakes another agent by mention only. |
|
|
87
|
+
| `"strict"` | Mention or named recipient only. |
|
|
88
|
+
| `"hand_raise"` | The floor decision runs on a person's message but nobody is woken; its answer arrives as the `conversation.hands_raised` event (`subscribeToEvents`) and the person picks who speaks, an explicit-recipient send. |
|
|
87
89
|
|
|
88
|
-
|
|
90
|
+
Mentions, a named recipient and `trigger_ai` answer in every mode. The kernel stores exactly these four values (`CHANNEL_AI_MODES`) and refuses any other at `create-channel` (`CHANNEL_AI_MODE_INVALID`); the legacy `on`/`off` rows were rewritten `on → active`, `off → strict`. A row the kernel has not rewritten is read the same way:
|
|
89
91
|
|
|
90
92
|
| Legacy/backend value | SDK value |
|
|
91
93
|
|----------------------|-----------|
|
|
92
|
-
| `"auto"` | `"
|
|
93
|
-
| `"mention"
|
|
94
|
-
| `"off"` | `"off"` |
|
|
95
|
-
| missing or unknown | `"off"` |
|
|
94
|
+
| `"on"`, `"auto"` | `"active"` |
|
|
95
|
+
| `"off"`, `"mention"`, missing or unknown | `"strict"` |
|
|
96
96
|
|
|
97
97
|
The SDK does not decide when AI should respond, spawn agents, or infer agent identity. It forwards gateway calls and normalizes read models; the kernel owns channel policy and message-trigger behavior.
|
|
98
98
|
|