SDK-79: Add LLM behavior eval support#189

Merged

benglewis merged 26 commits into

mainfrom

codex/2026-01-13/linear-mention-sdk-79-add-support-for-llm-behavior-eval

Feb 4, 2026

Commits on Jan 13, 2026

Commits on Jan 27, 2026

Merge branch 'main' into codex/2026-01-13/linear-mention-sdk-79-add-support-for-llm-behavior-eval
benglewis
committed

Commits on Jan 28, 2026

Basic first implementation of matching naming for `check_run` instead of `stream_results` and adding `tqdm`, unzipping and loading of CSVs
benglewis
committed
Add AGENTS.md and new `dependency_groups` entry of `dev` for development
benglewis
committed
Fix `RunStatus` circular dependency
benglewis
committed
Drop unnecessary `TypeAdapter` and add error log for invalid SSE payload to make it more debuggable
benglewis
committed
Update `AGENTS.md` to use context7 and not use 1-3 character variable names
benglewis
committed
Add assertion for `summary_brief` and `summary_full` to LLM behavior eval test
benglewis
committed
Fix SSE payload parsing
benglewis
committed
Try to fix `unzip` for LLM behavior eval results
benglewis
committed

Commits on Feb 4, 2026