fix: replace deprecated Pydantic class Config with model_config = ConfigDict()

v2.0 frontend: multi-step investigation UI with step tracker, progressive reveal, and reasoning bonus

v2.0: multi-step episodes, procedural bugs, semantic grading, sessions, 71 tests

Fix the comment

Fix all things

feat: serve frontend at root / so it shows in HF Spaces App tab, JSON status moved to /health

feat: add interactive demo frontend at /web — no existing endpoints changed

docs: comprehensive README with spec compliance checklist, log format, API examples

fix: add name/difficulty to tasks, per-task [START]/[END] logs for validator

fix: stateful endpoints + score clamping for validator pass

fix: all 0.0 defaults replaced with 0.05

fix: last remaining 0.0 in reset() total_score

fix: remove all 0.0/1.0 references, update reward ranges throughout

fix: reward_range to (0.05, 0.95) in environment.py TASKS_META

fix: reward_range changed to (0.05, 0.95) to satisfy strict bounds

fix: replace 0.0 fallback with 0.05 in graders to satisfy strict range

fix: correct [START] format, HF_TOKEN priority, remove /v1 forcing

fix: proper openenv.yaml with spec_version and task graders

Fix all things

fix: no exact 0.0 or 1.0 anywhere in rewards

fix: reward_range 0.05-0.95 and proper descriptions

fix: simplify openenv.yaml to match passing format

fix: correct grader import paths

Fix all things

fix: correct grader paths for validator

fix: add pydantic dependency for grader import

final fix: correct grader import to task module

fix: correct grader import path

fix: tasks returns plain array for validator

Fix all things

Fix all things

Fix all things

Fix all things

Fix all things

fix: replace asdict with model_dump in client.py step method

fix: validator anchor lines and reset keyword arg

fix: use pydantic .dict() instead of dataclasses asdict, remove raise exc

fix: inline BugTriageClient to eliminate import conflict

fix: use bug_triage_client to avoid openenv-core client conflict

fix: pass task_id as positional arg to reset()

fix: add openai to requirements - was causing silent import failure

fix: /v1 base_url, verbose logging, raise on exception

remove silent fallback in call_model

use API_KEY env var from eval proxy

use injected API_BASE_URL from eval proxy

fix grader import paths in openenv.yaml

update README with final scores and structure

remove duplicate task.py from root

Fix all things

fix: full grader paths