Spaces:

Nomearod
/

agentbench

Sleeping

App Files Files Community

agentbench / agent_bench /core /provider.py

Commit History

fix(judges,calibration,harness): three Codex adversarial-review findings

226b6f4

Nomearod Claude Opus 4.7 (1M context) commited on 30 days ago

chore(eval): pin gpt-4o-mini snapshot + wire fastapi golden_dataset + pre-commit tolerances

5c1f49f

Nomearod Claude Opus 4.6 (1M context) commited on Apr 14

feat: infrastructure sprint — vLLM/Modal, Helm, Terraform (#8)

a9d4375

Jane Yeung Claude Opus 4.6 (1M context) commited on Mar 31

feat: Anthropic Haiku benchmark + README with provider comparison

ade4c8b

Nomearod Claude Opus 4.6 (1M context) commited on Mar 25

feat: implement Anthropic Claude provider

077b821

Nomearod Claude Opus 4.6 (1M context) commited on Mar 25

feat: add streaming responses via SSE endpoint

7c40db3

Nomearod Claude Opus 4.6 (1M context) commited on Mar 25

feat: add provider retry with backoff and API rate limiting

871820a

Nomearod Claude Opus 4.6 (1M context) commited on Mar 25

fix: handle OpenAI rate limit / quota errors as 503 instead of 500

2a4cb78

Nomearod Claude Opus 4.6 (1M context) commited on Mar 24

fix: address Day 1 audit findings

e9173a5

Nomearod Claude Opus 4.6 (1M context) commited on Mar 24

feat: Day 1 — repo scaffolding, provider abstraction, config, tests

ef5d585

Nomearod Claude Opus 4.6 (1M context) commited on Mar 24