fix(nim): dynamically clamp max_tokens to resolve context window exhaustion (400 Bad Request)

fix(nim): classify expected context length / max context 400/500 errors as context_window_exceeded for automatic client compaction

fix(provider): remove invalid flush_task_arg_buffers call causing HTTP 500 error on streaming responses

feat: sync upstream commits up to f17c92bc

feat: apply upstream commits f077c358, 8696e132, cb5b4305

Revert "fix(nim): handle progressive payload downgrades on NIM 500 internal server errors"

fix(nim): handle progressive payload downgrades on NIM 500 internal server errors

fix(nim): pass body argument to _normalize_stream in KeyRotator loop to fix 502 error

feat: sync upstream 25th July commits (MiniMax-M3 native tool recovery, HTTP 403 permission denials)

fix(runtime): make startup model cache warming non-fatal on unconfigured providers

fix(api): allow unauthenticated GET to root path for HF Space health pings

feat: sync proxy with upstream commits up to a4a0fb8 (model catalog refactor, desktop launcher, telemetry feature flags)

fix(critical): replace super().__setattr__ with object.__setattr__ in ExecutionFailure to fix Python 3.12 slots+exception MRO crash causing 500 errors

fix(streaming): unconditionally strip Minimax control tokens and auto-close think tags on tool calls

fix(streaming): resolve chunking bug for tool call tag and control tokens

fix(streaming): parse minimax XML tool calls and strip control tokens

fix(streaming): remove Task tool buffering and fix thinking bypass

feat: intercept 404s to return 200 OK for scanner bots

fix(compatibility): resolve python 3.12 compatibility NameErrors and SyntaxErrors

fix(settings): use string literal type annotations for Settings class methods to support Python 3.12

fix(reasoning): use string literal type annotations for ReasoningPolicy classmethods to support Python 3.12

feat: synchronize proxy with upstream commits up to 5305bd7 and integrate NIM key rotator

chore(logs): silence uvicorn HEAD / health check logs

fix(nim): limit rate-limit retries to number of keys to prevent hanging

fix: replace super() with explicit calls to prevent async Python 3.12+ bug and suppress HEAD / logs

Fix: Bypass think_parser to emit raw thinking tags as plain text when reasoning isn't explicitly requested by client

Fix _PrefetchedStream asyncio task cancellation bug

Fix HF Space timeouts and infinite rotation loops

Fix tight RateLimitError loop causing timeouts by sleeping when keys are cooling down

Support x-api-key for auth in addition to Bearer tokens to fix Claude Code compatibility

Allow unauthenticated GET to root path so HF Space UI ping doesn't return 401

Deploy latest upstream with key rotation, vision adapter, and HF configs

fix: next_client typo and dataclass super() issue in ExecutionFailure

fix: implement missing _get_client methods for key rotation

fix: change timeout_s to http_read_timeout in Nim Provider initialization

fix: add missing inject_vision_into_request function

fix: update legacy core import in vision adapter

Deploy to Hugging Face Space