perf(logging): ⚡️ filter verbose litellm pre/post API call logs

chore(config): ⚙️ enable conditional instantiation of API call persistence

refactor(providers): 🔨 remove unsupported gemini preview models from hardcoded list in gemini CLI

feat(providers): ✨ inject NVIDIA 'thinking' flag for DeepSeek v3.1+ models

feat(client): ✨ add header fallback for custom_reasoning_budget

refactor(core): review fixes + improve error handling and execution logic

refactor(client): 🔨 comment out debug logging for litellm.acompletion kwargs

fix(providers): enhance rate limit error reliability in Gemini CLI

fix(rotator_library): ensure classify_error receives unwrapped exception

fix(proxy_app): 🐛 add type key to aggregated tool calls initialization

fix(providers): add model parameter to RateLimitError

fix(providers): improve error handling in streaming and rate limit scenarios

feat(providers): add tool choice translation for Gemini CLI provider

refactor(providers): refactor exception handling in Gemini CLI provider

feat(provider): add detailed transaction logging for gemini cli provider

refactor(providers): overhaul qwen code provider for custom streaming

fix(core): stabilize streaming for custom providers and refine usage recording

fix(providers): handle rate limit errors for gemini cli provider

fix(auth): persist resource URL during credential update

feat(auth): implement automatic project ID onboarding for Gemini CLI

refactor(auth): enhance OAuth credential structure for compatibility

fix(core): stabilize streaming for custom endpoints and eliminate initialization conflicts

refactor: improve model registration and usage manager robustness

feat(gemini-cli): implement tool use (function calling) and reasoning support

refactor(auth): generalize credential handling and improve model matching

feat(core): introduce model whitelisting to override blacklists

refactor(auth): implement two-pass OAuth credential deduplication

refactor(auth): refine duplicate OAuth credential checking logic

feat(auth): add interactive API key setup supporting 70+ providers

feat(auth): introduce dedicated --add-credential CLI utility

refactor(auth): standardize credential access and enhance interactive flow

refactor(auth): solidify Qwen device authorization flow and standardize credential access

feat(auth): implement automated credential discovery and duplication check

feat(auth): implement automated browser OAuth flow for Gemini

refactor(auth): enhance OAuth credential discovery and client logging

docs(config): document source of provider client IDs

refactor(client): simplify completion flow by removing internal streaming logic

fix(auth): resolve concurrent interactive prompts and token renewal issues

feat(auth): implement robust OAuth credential initialization and management

feat(provider): introduce OAuth credential management and custom provider handling

feat(proxy): ✨ implement detailed per-request transaction logging

feat(api): ✨ adopt OpenAI schema and blacklist patterns for model discovery

fix(proxy): handle None values in streaming tool-call aggregation

docs: update project descriptions and component names

feat(api): ✨ add CORS middleware to allow cross-origin requests

feat(client): set default include_usage for streaming responses

fix(client): sync key acquisition logging between stream/non-stream

feat(client): add pre-request callback support to API client

docs: restructure project licensing documentation

ci: pin release to commit SHA and refine client stream logging