Kirill Turanskiy 2ea95266e3 fix: clamp reasoning_effort to valid OpenAI-format values ...

CPA-internal thinking levels like 'xhigh' and 'minimal' are not accepted
by OpenAI-format providers (MiniMax, etc.). The OpenAI applier now maps
non-standard levels to the nearest valid reasoning_effort value before
writing to the request body:

  xhigh   → high
  minimal → low
  auto    → medium

2026-02-18 03:36:42 +03:00

..

access

refactor(sdk): simplify provider lifecycle and registration logic

2026-02-10 15:39:26 +08:00

api

refactor(all): replace manual pointer assignments with new to enhance code readability and maintainability

2026-02-15 14:10:10 +08:00

auth

fix(auth): normalize Gemini credential file prefix for consistency

2026-02-15 13:59:33 +08:00

browser

feat(logging): introduce centralized logging with custom format and Gin integration

2025-09-26 00:54:52 +08:00

buildinfo

feat(buildinfo): add build metadata and expose via HTTP headers

2025-11-13 08:38:03 +08:00

cache

test: align signature cache tests with cache behavior

2026-01-22 17:12:47 +08:00

cmd

refactor(all): replace manual pointer assignments with new to enhance code readability and maintainability

2026-02-15 14:10:10 +08:00

config

refactor(sdk): simplify provider lifecycle and registration logic

2026-02-10 15:39:26 +08:00

constant

**feat(translator): add Antigravity translation logic**

2025-11-21 23:40:59 +08:00

interfaces

**feat(antigravity): enhance handling of "thinking" content and refine Claude model response processing**

2025-12-07 13:19:12 +08:00

logging

fix(logging): expand tilde in auth-dir and log resolution errors

2026-02-03 00:02:54 +08:00

managementasset

fix(management): ensure management.html is available synchronously and improve asset sync handling

2026-02-09 08:32:58 +08:00

misc

refactor(codex): remove codex instructions injection support

2026-02-01 14:33:31 +08:00

registry

feat(registry): add Qwen 3.5 Plus model definitions

2026-02-16 22:55:37 +08:00

runtime

chore(runtime): update Qwen executor user agent and headers for compatibility with new runtime standards

2026-02-16 23:29:47 +08:00

store

fix(store): add proper GC with Handler and interval gating

2026-02-01 11:19:43 +07:00

thinking

fix: clamp reasoning_effort to valid OpenAI-format values

2026-02-18 03:36:42 +03:00

translator

Pass cache usage from codex to openai chat completions

2026-02-15 12:04:15 +07:00

usage

refactor(logger): remove unnecessary request details limit logic

2026-01-10 14:46:59 +08:00

util

fix(schema): remove Gemini-incompatible tool metadata fields

2026-02-11 18:29:17 +11:00

watcher

test(sdk/watcher): add tests for excluded models merging and priority parsing logic

2026-02-11 20:35:13 +08:00

wsrelay

refactor: consolidate channel send logic with context-safe handlers

2026-01-28 10:58:35 +08:00