@oneciel-ai/claude-any 0.1.30 → 0.1.32

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 CHANGED
@@ -44,7 +44,7 @@ arguments through unchanged.
44
44
 
45
45
  Credits: One Ciel LLC
46
46
 
47
- Current version: `0.1.30`
47
+ Current version: `0.1.32`
48
48
 
49
49
  ## Why This Exists
50
50
 
@@ -334,18 +334,31 @@ steps under that larger model's supervision.
334
334
 
335
335
  ## Changelog
336
336
 
337
- ### 0.1.30
337
+ ### 0.1.32
338
338
 
339
- - **Headless launch docs moved up**: README now shows copy-ready examples for
340
- launching Claude Code directly with `--ca-provider`, `--ca-model`, `-p`, and
341
- `CLAUDE_ANY_SKIP_MENU=1` immediately after install.
342
- - **NVIDIA hosted wording cleanup**: provider and lifecycle docs now describe
343
- NVIDIA hosted as using the Claude Any local router, with no separate hosted
344
- API Catalog proxy requirement.
339
+ - **NVIDIA preset menu fix**: LLM presets no longer try to apply the unsupported
340
+ `native` option for NVIDIA hosted, so selecting Long context / Large output
341
+ presets stays inside the menu instead of exiting.
345
342
 
346
- ### 0.1.29
343
+ ### 0.1.31
347
344
 
348
- - **NVIDIA compatibility test fix**: `claude-any test` now restarts the local
345
+ - **5-minute default upstream timeout**: existing saved 10/30-minute defaults
346
+ are migrated to 300000 ms so gateway stalls fail faster.
347
+ - **Localized gateway retries**: 502/503/504 and socket timeout responses are
348
+ retried automatically, with retry progress shown in the selected UI language.
349
+
350
+ ### 0.1.30
351
+
352
+ - **Headless launch docs moved up**: README now shows copy-ready examples for
353
+ launching Claude Code directly with `--ca-provider`, `--ca-model`, `-p`, and
354
+ `CLAUDE_ANY_SKIP_MENU=1` immediately after install.
355
+ - **NVIDIA hosted wording cleanup**: provider and lifecycle docs now describe
356
+ NVIDIA hosted as using the Claude Any local router, with no separate hosted
357
+ API Catalog proxy requirement.
358
+
359
+ ### 0.1.29
360
+
361
+ - **NVIDIA compatibility test fix**: `claude-any test` now restarts the local
349
362
  router before router-mode tests, so upgraded installs do not accidentally use
350
363
  an old long-running router that still expects `nvd-claude-proxy`.
351
364
  - **Clear NVIDIA router wording**: menu status now describes NVIDIA hosted as