@geminixiang/mikan 1.2.0 → 1.2.2

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 CHANGED
@@ -11,6 +11,33 @@ change in a minor release.
11
11
 
12
12
  ## [Unreleased]
13
13
 
14
+ ## [1.2.2] - 2026-10-09
15
+
16
+ ### Changed
17
+
18
+ - `jev_browser` writes the text it types or selects with the conversation's chat model, the one
19
+ the office's `settings.json` resolves, instead of `openai/gpt-4o-mini` called directly on
20
+ OpenRouter, so it no longer needs `OPENROUTER_API_KEY` and follows the office's provider.
21
+
22
+ ## [1.2.1] - 2026-10-09
23
+
24
+ ### Added
25
+
26
+ - Jev uses the first of pi-ai's built-in Jev models whose provider has a key, starting with
27
+ OpenRouter and then TypeSafe, Vercel AI Gateway, Cloudflare Workers AI, and OpenCode, so it
28
+ works with `TYPESAFE_API_KEY` and the other providers Pi lists, not only `OPENROUTER_API_KEY`.
29
+ - A `models.json` entry that gives a built-in provider only a `baseUrl` and an `apiKey`, as Pi
30
+ documents for proxies, now also redirects that provider's classifier models and uses that key.
31
+ Jev reads the daemon's `models.json`, so `"typesafe": { "baseUrl": …, "apiKey": … }` sends Jev
32
+ through a System One proxy without an OpenRouter key.
33
+
34
+ ### Removed
35
+
36
+ - The `jev` setting and the `models.json` classifier models added in 1.2.0 are removed, so
37
+ `models.json` follows Pi's format again. To send Jev through a gateway, use the built-in
38
+ provider override above. `jev_browser` again writes form text with `openai/gpt-4o-mini` on
39
+ OpenRouter, as in 1.1.0, so it still needs `OPENROUTER_API_KEY`.
40
+
14
41
  ## [1.2.0] - 2026-10-09
15
42
 
16
43
  ### Added
@@ -1264,7 +1264,7 @@ export class SlackMessagingBot {
1264
1264
  }
1265
1265
  catch (err) {
1266
1266
  if (err instanceof JevNotConfiguredError) {
1267
- log.logWarning("Slack auto-reply jev mode has no Jev model available; treating message as unaddressed", String(err));
1267
+ log.logWarning("Slack auto-reply jev mode has no Jev provider key; treating message as unaddressed", String(err));
1268
1268
  return false;
1269
1269
  }
1270
1270
  reportUserFacingError(err, {