Tyler Ford 52e6a8b80f fix: model-aware supportsRedactedThinking for mixed-format providers (#4479) ...

Thanks @TF0rd! Rebased onto release/v3.8.32. Added the missing regression test for the model-aware redacted_thinking branch (Rule #18): minimax-m3 (claude format) gets redacted_thinking, glm-5.1 (openai) stays plain. 3/3.

2026-06-21 08:48:06 -03:00

..

config

feat(providers): expand openai/gemini direct registries with first-class missing variants (#4394)

2026-06-20 17:05:11 -03:00

executors

fix(command-code): pass reasoning/thinking fields through to params (#4473)

2026-06-21 08:36:25 -03:00

handlers

refactor(chatCore): extrai resolvers de service-tier do Codex para leaf puro (#3501) (#4477)

2026-06-21 08:30:20 -03:00

lib

Release v3.8.4 (#2678)

2026-05-26 23:51:47 -03:00

mcp-server

feat(mcp): register web-session pool observability tools (#3368) (#4399)

2026-06-20 16:53:09 -03:00

services

feat(usage): support quota fetch for kimi-coding-apikey (#4435)

2026-06-21 08:45:56 -03:00

transformer

Release v3.8.28 (#4053)

2026-06-17 19:26:32 -03:00

translator

fix: model-aware supportsRedactedThinking for mixed-format providers (#4479)

2026-06-21 08:48:06 -03:00

utils

fix(sse): refactor stall detection to reduce false positives on slow but progressing streams (#4456)

2026-06-20 20:26:42 -03:00

.npmignore

feat: OmniRoute v1.0.0 — Intelligent AI Gateway & Universal LLM Proxy

2026-02-18 00:02:15 -03:00

index.ts

feat: add ModelScope provider with circuit breaker and daily quota lock (#1430)

2026-04-19 21:13:45 -03:00

package.json

chore(release): open v3.8.32 development cycle

2026-06-20 15:29:52 -03:00

tsconfig.json

Release v3.8.23

2026-06-12 23:49:22 -03:00

types.d.ts

fix(api): harden model tests and metadata reads

2026-04-25 14:41:45 -03:00