40 Ревизии (1a98836b94bfbe27de758ca6aea7c0d7e14fba7e)
 

Автор SHA1 Съобщение Дата
  orangels 1a98836b94 fix: set bench max tokens default to 200k преди 1 месец
  orangels 948e32d64a feat: log request errors for debug преди 1 месец
  orangels f17c0af5d7 feat: tighten aime final answer parsing преди 1 месец
  orangels e0aca08f36 feat: align gpqa scoring with simple evals преди 1 месец
  orangels 898d02f7ef feat: record upstream error debug payloads преди 1 месец
  orangels 5706ac8ee8 feat: add google gemini protocol преди 1 месец
  orangels 6959de5eac docs: add CLAUDE.md and update config.example.yaml преди 1 месец
  orangels 18cc7ff716 feat: add provider thinking parameters преди 1 месец
  orangels ee13739c5e feat: add raw response debug mode преди 1 месец
  orangels 60cc009c83 fix: support bare stream flag and cover SSE parsing преди 1 месец
  orangels f21ab8bd4c feat: add --max-tokens CLI param and correct_samples to bench reports преди 1 месец
  orangels 4988a86654 feat: add progress bars to benchmark and RPM execution преди 1 месец
  orangels 527b1e8fc7 feat: add params field to RPM and benchmark reports преди 1 месец
  orangels e269f8f99d docs: add end-to-end testing guide for RPM and benchmarks преди 1 месец
  orangels fdb437a732 fix: correct streaming bugs and RPM diagnose gaps преди 1 месец
  orangels 20217b2250 feat: add streaming (SSE) support with TTFT metrics преди 1 месец
  orangels f5b9239167 docs: add Chinese usage guide преди 1 месец
  orangels 84943db37a docs: document rpm limiter modes преди 1 месец
  orangels 2b9fae7ebd feat: report rpm limiter mode details преди 1 месец
  orangels 0a96e11e98 feat: run rpm limiter modes преди 1 месец
  orangels 7c0d1e8af0 feat: add rpm mode schedules преди 1 месец
  orangels f6b09d00a4 docs: plan rpm limiter modes преди 1 месец
  orangels 65ce102004 fix: resolve only selected provider env refs преди 1 месец
  orangels 4b433c25e6 fix: redact config tokens in debug output преди 1 месец
  orangels 31c41cb8ac fix: satisfy final clippy checks преди 1 месец
  orangels 4e99ab6f37 docs: add usage guide преди 1 месец
  orangels 83edc789df fix: make benchmark and rpm execution reliable преди 1 месец
  orangels 5d1163d635 feat: run benchmark and rpm tests преди 1 месец
  orangels 4a0e187e98 docs: specify benchmark report output преди 1 месец
  orangels d0fed7b680 fix: harden protocol adapter errors преди 1 месец
  orangels 1e0926cfba feat: add openai and anthropic request adapters преди 1 месец
  orangels 2064c69924 fix: tighten benchmark dataset helpers преди 1 месец
  orangels 67a4ea8af4 feat: add benchmark dataset fetch and prompts преди 1 месец
  orangels 690b815ae0 test: avoid global env mutation in config tests преди 1 месец
  orangels b071c99ee6 feat: load yaml relay config преди 1 месец
  orangels c0ebdea077 chore: initialize cli project skeleton преди 1 месец
  orangels ea0b255547 docs: add implementation plan преди 1 месец
  orangels 61446dcf9f docs: define benchmark dataset download flow преди 1 месец
  orangels 6e804b917f docs: use official gsm8k benchmark преди 1 месец
  orangels 884097722f docs: add design spec преди 1 месец