Commit Graph

12 Commits

Author SHA1 Message Date
Diego Rodrigues de Sa e Souza
3d75fb3fae Release v3.8.0 (#2073)
Integrated into release/v3.8.0
2026-05-10 00:55:06 -03:00
backryun
a16e47c593 fix(providers): refresh web client user agents (#1699)
Integrated release/v3.7.2 changes — refreshed web client user agents, env docs, Gemini OAuth fix
2026-04-28 02:41:19 -03:00
diegosouzapw
cb4ad33703 fix(api): harden model tests and metadata reads 2026-04-25 14:41:45 -03:00
backryun
a5be284f1d [Improvement] Fix Providers Default models list (Done) (#1577)
Integrated into release/v3.7.0
2026-04-25 11:03:31 -03:00
diegosouzapw
7d34b6a7e1 feat(providers): add AWS Polly and Lemonade provider support
Register AWS Polly as an audio provider with SigV4 request signing,
speech engine discovery, and API-key validation for managed provider
flows.

Add Lemonade as a self-hosted OpenAI-compatible provider, expand
static model discovery to audio registries, and support Azure OpenAI
deployment discovery from resource endpoints.

Sanitize sensitive provider-specific AWS fields in API responses and
update related tests and release notes.
2026-04-24 13:20:59 -03:00
Cong Vu Chi
15b4a54454 fix(claude): preserve tool_result adjacency (#1555)
* fix(claude): preserve tool_result adjacency in native and CC-compatible paths

* feat(providers): add Petals and Nous Research provider support

Register Nous Research as an OpenAI-compatible gateway with remote
model discovery and validation against chat completions.

Add Petals provider metadata, default config, validation, and a
specialized executor that maps OpenAI-style requests to the public
generate endpoint. Also allow optional API keys and configurable base
URLs for Petals in the dashboard and provider schemas.

Expand provider model and catalog tests to cover both integrations.

* fix(resilience): sync queue updates and clear stale discovery caches

Await runtime request queue updates so limiter settings and auto-enabled
API key protections are recomputed when resilience settings change.

Preserve cancelled batch state for in-flight work by marking input files
processed without generating output artifacts, and replace cached synced
models with an empty set when remote discovery returns no models so the
providers route falls back to the local catalog instead of stale cache.

---------

Co-authored-by: congvc <congvc-dev@gmail.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
2026-04-24 09:22:46 -03:00
diegosouzapw
16b0499192 fix(api): harden batch and file endpoints for auth and recovery
Reject invalid API keys even when authentication is optional and add
OPTIONS handlers for batch and file routes to support CORS preflights.

Also recover orphaned batches stuck in finalizing after restarts,
include finalizing in pending batch queries, preserve multipart upload
content handling, and fetch remote vision images as data URIs for
Anthropic requests.
2026-04-22 17:10:47 -03:00
diegosouzapw
a7b6dfb06e chore: apply PR 1495 and update changelog 2026-04-21 21:12:29 -03:00
Markus Hartung
098639e146 fix: add batch item dispatching to specific handlers based on URL (#1495)
Integrated into release/v3.7.0
2026-04-21 21:10:38 -03:00
diegosouzapw
a7d30d9c6f test: isolate batch API unit tests with temp DATA_DIR to prevent schema state collisions 2026-04-21 19:32:20 -03:00
Markus Hartung
2e36599d40 fix: resolve code rebase issues 2026-04-21 22:53:19 +02:00
Markus Hartung
03769eb0ea feat: add support for OpenAI batch processing 2026-04-21 15:12:12 +02:00