VXNCXNX a5a78fd1d8 fix(kiro): preserve GPT-5.6 Max reasoning via Responses (#9163) ...

Validated in local merge-train (devbox-vm-06-dev002) @ combined-tip (FAST gates green: static + changed tests + vitest — only pre-existing audit.test.ts flake). Evidence: /home/diegosouzapw/dev/proxys/OmniRoute/.claude/worktrees/merge-train-20260805-213228-suite.log

2026-08-05 21:44:02 -03:00

..

helpers

fix(kiro): preserve GPT-5.6 Max reasoning via Responses (#9163)

2026-08-05 21:44:02 -03:00

image

fix(types): cast extracted usage to Record<string,number> in stream.ts to resolve TS property errors

2026-03-23 09:21:03 -03:00

request

fix(kiro): preserve GPT-5.6 Max reasoning via Responses (#9163)

2026-08-05 21:44:02 -03:00

response

fix(translator): join reasoning summary segments with newline separators (#9500)

2026-08-05 16:49:37 -03:00

bootstrap.ts

fix(translator): register openai response projection for gemini clients (#7207)

2026-07-17 10:39:35 -03:00

deepseekWebTools.ts

fix(security): require explicit tool envelope to prevent bare JSON tool_calls (#9343)

2026-08-04 23:28:33 -03:00

formats.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00

index.ts

fix(sse): stop thrashing the provider prompt cache for caching-aware clients (#8705)

2026-07-27 17:24:43 -03:00

paramSupport.ts

fix(routing): strip prompt_cache_key for NVIDIA NIM (#7617) (#7709)

2026-07-19 02:31:15 -03:00

registry.ts

feat: add TypeScript types and modularize translator registry

2026-03-04 18:46:49 -03:00

webTools.ts

fix(security): require explicit tool envelope to prevent bare JSON tool_calls (#9343)

2026-08-04 23:28:33 -03:00