Spaces:
Sleeping
Sleeping
Commit History
-
Load cross-project shared.env before project .env for local dev.
Jordan Miller +1: CursorAuto-detect secrets at ~/.secrets/shared.env or ~/Downloads/shared.env so API keys stay outside the repo while docker-compose and dev-local.sh can opt in via SHARED_ENV_FILE. Co-authored-by: Cursor <[email protected]>40dee71
-
Make local docker compose port-overridable; fix lockfile drift
NeonClary +1: Cursor- docker-compose.yml: host port now reads from ${CCAI_HOST_PORT:-7860} so local devs can sidestep port conflicts (e.g. set CCAI_HOST_PORT=3002 in .env) without editing the compose file. Default stays 7860 for HuggingFace Space parity. - Dockerfile: frontend stage bumped from node:20-alpine to node:22-alpine so the in-container npm matches the host npm 11 that maintains the lockfile. Without this, npm ci inside the container failed with a "Missing [email protected] from lock file" lockfile-drift error. - frontend/package-lock.json: regenerated cleanly so `npm ci` is reproducible across hosts. - .gitignore: ignore docker-compose.override.yml (used for local-only port + env_file overrides) and the transient .commit-msg.txt buffer. Co-authored-by: Cursor <[email protected]>e03c7d3 -
Build CCAI Vibe Demo on top of LLMChats3 baseline
NeonClary +1: CursorMulti-participant Collaborative Conversational AI demo: the orchestrator runs a six-phase state machine (Initial Opinions, Critique x2, Status Assessment, Finalization, Consensus, Closure), produces a JSON Credential Summary keyed on credibility-for-question, and routes addressed-to messages through alliance detection. Two failsafes - 60+20 participant messages and 100+50 orchestrator calls - pause the loop until the user clicks Continue. Every LLM response is funneled through a centralized strip_thinking sanitizer before being stored, displayed, or fed back to the summarizer. Backend - New: services/{models,prompts/*,credential,consensus,context_budget, json_calls,extra_personas,orchestrator}.py, utils/sanitize.py, api/personas.py, data/demo_questions.json (10 long-context prompts). - Rewrote api/chat.py with /chat/start (N participants, summarizer + max-participants overrides), /chat/{id}/continue, table-view + csv-table exports. - Rate limit bumped to 30/day per IP; HF org …0bb4dfa -
Import LLMChats3 master as CCAI baseline
NeonClary +1: CursorCo-authored-by: Cursor <[email protected]>c44fab6