Fix health endpoint to report env=real (built-in env is fully functional)

Merge branch 'master' into master

Add model-driven local runtime and dynamic demo flow

Fix gpt-5.4 incompatibility: use max_completion_tokens instead of max_tokens

Switch Oracle judge to OpenAI (gpt-5.4), support both backends

Fix scientist inference and wire Oracle LLM judge

Wire fine-tuned Qwen3.5 LoRA checkpoint into scientist suggest endpoint

Use generic regex for CORS instead of hardcoded deployment URLs

Add Northflank CORS origins for production deployment

Finalize demo flow and training assets

Merge remote-tracking branch 'origin/master' into ayush

frontend changes

Add API 19 /web fallback route, merge Kush frontend, close UI 07

Add ENV 09 disk persistence, OBS 07/09, TST 11 audit tests, close 10 Max tasks

Add hybrid Oracle layer and update architecture docs

Recover env judge training stack and sync project tracking

Recover env server client stack and deployment tracking

Add AGT 04/05/07 implementations, server integration, and doc updates

Type EpisodeState and EpisodeLog with Protocol, ConversationEntry, RewardBreakdown (MOD 04)

Add MOD 11 typed StepInfo/RewardBreakdown and import completed foundation modules

Add future improvements doc, import FND 09 and MOD 01-03 completions

Import and normalize Max backend scaffold with validated partial status

Complete FND 01 and FND 10, update task division with status tracking