track binary files with git-lfs

Merge pull request #1519 from router-for-me/thinking

fix(registry): correct max completion tokens for opus 4.6 thinking

feat(translator): support Claude thinking type adaptive

refactor(sdk): simplify provider lifecycle and registration logic

docs(config): reorder antigravity model alias example

docs(config): simplify oauth model alias example

Merge pull request #1506 from masrurimz/fix-sse-model-mapping

ci: retrigger workflows

fix(amp): rewrite model name in response.model for Responses API SSE events

Merge pull request #1502 from router-for-me/iflow

Merge pull request #1492 from router-for-me/management

feat(executor): add session ID and HMAC-SHA256 signature generation for iFlow API requests

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

Fixed: #1484

Merge pull request #1479 from router-for-me/management

fix(config): prune default descendants when merging new yaml nodes

fix(config): avoid writing known defaults during merge

refactor(management): streamline control panel management and implement sync throttling

Merge pull request #1467 from dusty-du/fix/kimi-toolcall-reasoning-content

chore(docs): remove Cubence sponsorship from README files and delete related asset

fix(kimi): reduce redundant payload cloning and simplify translation calls

fix(translator): correct gemini-cli log prefix

fix(kimi): update base URL and integrate ClaudeExecutor fallback

Fix Kimi tool-call reasoning_content normalization

Merge pull request #1390 from sususu98/fix/400-invalid-request-no-retry

Merge pull request #1386 from shenshuoyaoyouguang/sync-auth-changes

Merge pull request #1239 from ThanhNguyxn/fix/gitstore-gc-after-squash

fix(translator): normalize and restrict `stop_reason`/`finish_reason` usage

Merge pull request #1465 from router-for-me/kimi-fix

fix(kimi): add OAuth model-alias channel support and cover OAuth excluded-models with tests

feat(translator): capture cached token count in usage metadata and handle prompt caching

Merge branch 'kimi-provider-support-v2' into dev

feat: add Kimi authentication support and streamline device ID handling

refactor(config): disable automatic migration during server startup

Add Kimi (Moonshot AI) provider support

Merge pull request #1435 from tianyicui/fix/haiku-4-5-thinking-support

Merge pull request #1446 from qyhfrank/fix-claude-opus-4-6-model-metadata

fix(registry): correct Claude Opus 4.6 model metadata

refactor(executor): centralize Codex client version and user agent constants

refactor(translator, executor): remove redundant `bytes.Clone` calls for improved performance

Merge pull request #1440 from kvokka/add-cc-opus-4-6

feat(registry): register Claude 4.6 static data

feat(registry): add GPT 5.3 Codex model to static data

refactor(executor): optimize payload cloning and streamline SDK translator usage

refactor(util): optimize JSON schema processing and keyword removal logic

feat(registry): add Kimi-K2.5 model to static data

fix: Enable extended thinking support for Claude Haiku 4.5

refactor(util, executor): optimize payload handling and schema processing

Merge pull request #1429 from neavo/fix/gemini-python-sdk-thinking-fields