Commit History

Автор SHA1 Съобщение Дата
  Ketan Ramaneti 852c90f64a [fix eval] Fix issues with miniwob remote runtime evaluation (#5001) преди 1 година
  Ketan Ramaneti 42b49e6c43 [fix eval] Fix issues with aider_bench remote runtime evaluation (#5000) преди 1 година
  Robert Brennan 17f4c6e1a9 Refactor sessions a bit, and fix issue where runtimes get killed (#4900) преди 1 година
  Engel Nyst eeb2342509 Refactor history/event stream (#3808) преди 1 година
  Xingyao Wang 966da7b7c8 feat(agent, CodeAct 2.2): native CodeAct support for Browsing (#4667) преди 1 година
  Xingyao Wang 1f23dc89b6 fix(eval): add runtime.connect to all eval harness (#4565) преди 1 година
  Xingyao Wang 2d5b360505 refactor: re-organize different runtime implementations into an impl folder (#4346) преди 1 година
  Xingyao Wang b23c7aab5a [eval] stop set sid in eval (#4311) преди 1 година
  Aditya Bharat Soni 0809d26f4d fix: Allow evaluation benchmarks to pass image urls in run_controller() instead of simply passing strings (#4100) преди 1 година
  Xingyao Wang 090c911a50 (refactor) Make `Runtime` class synchronous (#3661) преди 1 година
  Graham Neubig f9088766e8 Allow setting of runtime container image (#3573) преди 1 година
  Robert Brennan 01ae22ef57 Rename OpenDevin to OpenHands (#3472) преди 1 година
  Xingyao Wang b30a2dd87a completely remove update_source_code (#3280) преди 1 година
  Xingyao Wang 31b244f95e [Refactor, Evaluation] Refactor and clean up evaluation harness to remove global config and use EventStreamRuntime (#3230) преди 1 година
  Xingyao Wang 001195a3ea reduce the duplication in run_controller (#3217) преди 1 година
  Xingyao Wang 4f0a454ed6 [Arch] Support integration tests using EventStream Runtime (#3184) преди 1 година
  tobitege 70dd705418 Fix: apply config arguments for miniwob get_sandbox() from loaded config (#3198) преди 1 година
  Graham Neubig 275ea706cf Remove remaining global config (#3099) преди 1 година
  Xingyao Wang da17665cab fix: make max_budget_per_task optional in `run_agent_controller` (#3071) преди 1 година
  Xingyao Wang cf910dfa9d fix eval api_key leak in metadata; fix llm config in run infer (#2998) преди 1 година
  Engel Nyst d37b2973b2 Refactoring: event stream based agent history (#2709) преди 1 година
  Graham Neubig d0384cafdd Two fixes to swe bench eval (#2831) преди 1 година
  Xingyao Wang f6dc89b41a [Evaluation] Simplify eval & and multi-processing related fixes (#2810) преди 1 година
  Graham Neubig a081935fd8 Simplify eval code (#2775) преди 1 година
  Graham Neubig ffd3c7144c Remove global args (#2760) преди 1 година
  Engel Nyst 2d9bb56763 Add ability to restore the cli session (optional) (#2699) преди 1 година
  Engel Nyst 874b4c9075 CLI concurrency (#2695) преди 1 година
  RainRat 745ae42a72 fix typos (#2352) преди 1 година
  Frank Xu 48151bdbb0 [feat] WebArena benchmark, MiniWoB++ benchmark and related arch changes (#2170) преди 1 година