52 Commits (main)
 

Autor SHA1 Nachricht Datum
  liushen ffb25b0126 Merge pull request 'codex/lq-token-test-init' (#2) from codex/lq-token-test-init into main vor 1 Monat
  orangels c346233072 feat: record stream chunk timings in reports vor 1 Monat
  orangels 1f5bdb26f6 feat: group reports by local date vor 1 Monat
  orangels 506434da6a fix: use local time for raw debug logs vor 1 Monat
  orangels 4e0d85205a feat: group raw debug logs by date vor 1 Monat
  orangels 70ced01112 feat: record response debug cases in reports vor 1 Monat
  orangels a15a62264a fix: set bench max tokens default to 64k vor 1 Monat
  orangels 1243558bc8 fix: include partial stream in interrupted debug logs vor 1 Monat
  orangels 739524628c feat: report effective benchmark request params vor 1 Monat
  liushen 91e863b448 Merge pull request 'codex/lq-token-test-init' (#1) from codex/lq-token-test-init into main vor 1 Monat
  orangels 986dc4e088 fix: restore bench max tokens default vor 1 Monat
  orangels b5d83f948b fix: log empty successful responses as request errors vor 1 Monat
  orangels 1a98836b94 fix: set bench max tokens default to 200k vor 1 Monat
  orangels 948e32d64a feat: log request errors for debug vor 1 Monat
  orangels f17c0af5d7 feat: tighten aime final answer parsing vor 1 Monat
  orangels e0aca08f36 feat: align gpqa scoring with simple evals vor 1 Monat
  orangels 898d02f7ef feat: record upstream error debug payloads vor 1 Monat
  orangels 5706ac8ee8 feat: add google gemini protocol vor 1 Monat
  orangels 6959de5eac docs: add CLAUDE.md and update config.example.yaml vor 1 Monat
  orangels 18cc7ff716 feat: add provider thinking parameters vor 1 Monat
  orangels ee13739c5e feat: add raw response debug mode vor 1 Monat
  orangels 60cc009c83 fix: support bare stream flag and cover SSE parsing vor 1 Monat
  orangels f21ab8bd4c feat: add --max-tokens CLI param and correct_samples to bench reports vor 1 Monat
  orangels 4988a86654 feat: add progress bars to benchmark and RPM execution vor 1 Monat
  orangels 527b1e8fc7 feat: add params field to RPM and benchmark reports vor 1 Monat
  orangels e269f8f99d docs: add end-to-end testing guide for RPM and benchmarks vor 1 Monat
  orangels fdb437a732 fix: correct streaming bugs and RPM diagnose gaps vor 1 Monat
  orangels 20217b2250 feat: add streaming (SSE) support with TTFT metrics vor 1 Monat
  orangels f5b9239167 docs: add Chinese usage guide vor 1 Monat
  orangels 84943db37a docs: document rpm limiter modes vor 1 Monat
  orangels 2b9fae7ebd feat: report rpm limiter mode details vor 1 Monat
  orangels 0a96e11e98 feat: run rpm limiter modes vor 1 Monat
  orangels 7c0d1e8af0 feat: add rpm mode schedules vor 1 Monat
  orangels f6b09d00a4 docs: plan rpm limiter modes vor 1 Monat
  orangels 65ce102004 fix: resolve only selected provider env refs vor 1 Monat
  orangels 4b433c25e6 fix: redact config tokens in debug output vor 1 Monat
  orangels 31c41cb8ac fix: satisfy final clippy checks vor 1 Monat
  orangels 4e99ab6f37 docs: add usage guide vor 1 Monat
  orangels 83edc789df fix: make benchmark and rpm execution reliable vor 1 Monat
  orangels 5d1163d635 feat: run benchmark and rpm tests vor 1 Monat
  orangels 4a0e187e98 docs: specify benchmark report output vor 1 Monat
  orangels d0fed7b680 fix: harden protocol adapter errors vor 1 Monat
  orangels 1e0926cfba feat: add openai and anthropic request adapters vor 1 Monat
  orangels 2064c69924 fix: tighten benchmark dataset helpers vor 1 Monat
  orangels 67a4ea8af4 feat: add benchmark dataset fetch and prompts vor 1 Monat
  orangels 690b815ae0 test: avoid global env mutation in config tests vor 1 Monat
  orangels b071c99ee6 feat: load yaml relay config vor 1 Monat
  orangels c0ebdea077 chore: initialize cli project skeleton vor 1 Monat
  orangels ea0b255547 docs: add implementation plan vor 1 Monat
  orangels 61446dcf9f docs: define benchmark dataset download flow vor 1 Monat