@pidgeon-ai/sdk 1.13.0 → 1.14.0
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/CHANGELOG.md +9 -0
- package/dist/index.d.cts +1 -0
- package/dist/index.d.ts +1 -0
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -9,6 +9,15 @@ call shapes, the result shape — not to the API behind it.
|
|
|
9
9
|
|
|
10
10
|
## Unreleased
|
|
11
11
|
|
|
12
|
+
## 1.14.0 — clean bodies in a conversation
|
|
13
|
+
|
|
14
|
+
`body=clean` on `GET /messages`, as on `GET /messages/{id}` and
|
|
15
|
+
`/messages/await`: every message in the conversation comes back with
|
|
16
|
+
Pidgeon Firewall's `clean_text` as its text and empty HTML. The MCP
|
|
17
|
+
`list_messages` tool asks for it by default. And a message the Firewall
|
|
18
|
+
calls suspicious is stored with a preview cut from its cleaned text, so a
|
|
19
|
+
hidden instruction no longer shows in search results or folder listings.
|
|
20
|
+
|
|
12
21
|
## 1.13.0 — what the agent reads
|
|
13
22
|
|
|
14
23
|
`firewall.clean_text` on every inbound message: the new text with hidden
|
package/dist/index.d.cts
CHANGED
package/dist/index.d.ts
CHANGED