fix: compute dynamic initial values for active p1 and available units on reset observation

feat: exploit analysis, architecture docs, observation depth, citation

fix: package live_dashboard.html into docker image

fix: robust absolute path fallback for live_dashboard html rendering

fix: serve live_dashboard.html on root route instead of json

Merge branch 'main' of https://github.com/garvitsachdevaa/911-Dispatch-Supervisor

feat: phase3 improvements - reward clarity, survival clocks, MCP endpoint, phraseology docs

Add root endpoint for HF Space probes

Add HF Space YAML frontmatter

fix(api): remove Pydantic model for /reset to natively handle null JSON bodies from OpenEnv validator

This is the second End

fix: revert inference format and make /reset payload optional

This is the End

fix: port 7860, pip setup, real baseline scores, router API URL, MCP endpoint, LLM prompt

Submission polish: compliance hardening, baseline matrix, dashboard UX, tests, and docs

Remove changes.md from repository

Clean up README

Readme updated

docs: polish README; remove emoji

Improve shift_surge grading and phraseology-based protocol reward

Expand action space: stage, reassign, mutual aid, severity change

Unify OpenEnv and benchmark episode scoring

Unify benchmark scoring with OpenEnv episode reward

Fix triage reward lookup for enum-qualified metadata

Finalize OpenEnv baseline: OpenAI client, PORT binding, and docs

Add OpenEnv runtime endpoints

Make openenv validate pass

Apply changes.md compliance fixes

Fix OpenEnv metadata, docker data, tasks endpoint, and demo

Dispatch environment: rewards, dashboard, docs, and passing tests

Rename project slug; remove architecture.md

Initial import: 911 dispatch RL environment