v0.0.3

What's Changed

• safety challenges, adaptability challenges, suite same_task by @SilenNaihin in #177
• Beat more challenges in Auto-GPT by @merwanehamadi in #187
• Uninstall agbenchmark then reinstall by @merwanehamadi in #188
• Fix helicone MITM by @merwanehamadi in #189
• Add api keys by @merwanehamadi in #190
• hotfix reports by @SilenNaihin in #191
• Update Scores Benchmark by @merwanehamadi in #192
• fix suite dependencies by @SilenNaihin in #194
• Add safety suite by @merwanehamadi in #196
• report # bug, adding submodule challenges by @SilenNaihin in #193
• Add llm eval by @merwanehamadi in #197
• ci update by @SilenNaihin in #198
• Add helicone dynamic headers by @merwanehamadi in #199
• Add dynamic headers using environment variables by @merwanehamadi in #200
• added new script to fix dynamic headers by @chitalian in #202
• Delete reports by @merwanehamadi in #201
• Use beebot autopackai by @merwanehamadi in #203
• Benchmark all test by @merwanehamadi in #204
• Fix tests not being run by @merwanehamadi in #207
• Retry push until successful by @merwanehamadi in #208
• Advanced LLM Evaluation Implementation by @SilenNaihin in #205
• returning scores by @SilenNaihin in #210
• Update submodules by @merwanehamadi in #212
• Use Auto-GPT master by @merwanehamadi in #213
• Fix export to gdrive by @merwanehamadi in #214
• Add timeout to agbenchmark by @merwanehamadi in #215
• Add timeout that allows teardown by @merwanehamadi in #216
• Delete incorrect report by @merwanehamadi in #217
• Feature: Visualize Test Results by @SilenNaihin in #211
• Fix timeout not working by @merwanehamadi in #218
• Update submodule by @merwanehamadi in #219
• Get helicone costs by @merwanehamadi in #220
• working bar and radar charts by @SilenNaihin in #221
• Fix f-string get_data_from_helicone.py by @chitalian in #223
• Fix BeeBot link by @MrBrain295 in #224
• Fix send to gdrive and tracking the wrong challenge name by @merwanehamadi in #225
• Refactoring for TDD by @SilenNaihin in #222
• Fix costs helicone by @merwanehamadi in #226
• Fix reports by @merwanehamadi in #227
• Return none as fallback Helicone by @merwanehamadi in #228
• Only run mini-agi on push and PR by @merwanehamadi in #230
• Reverse skip based on agent by @merwanehamadi in #231
• Only run mini-agi on tests by @merwanehamadi in #232
• Fix reports and add commit sha by @merwanehamadi in #233
• Send commit sha and cost to gdrive by @merwanehamadi in #234
• Remove high costs by @merwanehamadi in #235
• Remove mock reports by @merwanehamadi in #236
• Remove mock reports by @merwanehamadi in #237
• Update beebot and Auto-GPT by @merwanehamadi in #238
• Update autogpt back to where it was by @merwanehamadi in #239
• Update python-dotenv by @erik-megarad in #240
• Update Auto-GPT and allow 1 specific agent to be run by @merwanehamadi in #241
• Add attempted metrics by @merwanehamadi in #244
• Correct agent and benchmark commit sha by @merwanehamadi in #245
• fix-linter by @merwanehamadi in #246
• Fix typing by @merwanehamadi in #247
• Add Test Suite to gdrive by @merwanehamadi in #248
• Release 0.0.3 by @merwanehamadi in #249

New Contributors

• @chitalian made their first contribution in #202
• @MrBrain295 made their first contribution in #224

Full Changelog: v0.0.2...v0.0.3