open-thoughts/OpenThoughts-Agent - Page 2

serve-model-vibe-test

Stand up a PUBLIC, shareable inference endpoint for an HF/gs model on an Iris TPU so people on the internet can vibe-test it in a browser or via an OpenAI-compatible API. Use when asked to "serve a model for testing", "throw up a public endpoint", "let people…

sft-cleanup-hf-only

Clean up a completed NON-AGENTIC / HF-only SFT model — HF upload WITHOUT Supabase DB registration. The counterpart to sft-job-cleanup (which uploads AND registers). Use when a completed SFT cell belongs to an HF-only series (config `enable_db_registration:…

sft-job-cleanup

Publish + clean up a finished LLaMA-Factory SFT job on a no-internet HPC cluster (Jupiter/Leonardo): cancel pending retries, drop intermediate checkpoints, HF-upload the model to its configured --hub_model_id, register in Supabase via manual_db_push…

sft-launch

Launch SFT via `python -m hpc.launch --job_type sft` on any cluster (JSC Jupiter GH200, CINECA Leonardo A100, TACC Vista GH200), with EITHER backend — LLaMA-Factory (default) or axolotl (`--sft_backend axolotl`) — including Delphi tool-calling models (delphi…

supervisor-init

Bootstrap the supervisor role at the start of a session — the human-facing lab supervisor who manages a large multi-experiment ML-ops operation: the single interface between the user and subagents / crons / top-level tools, keeper of secrets, and tracker of…

utils-cleanup-stale-sandboxes

Delete stale Daytona sandboxes across ALL THREE orgs (DataComp, DataCompData, DataCompRL) in one pass. Runs `scripts/daytona/cleanup_stale_sandboxes.py` three times — once per org — each time setting the org's API key via `--api-key-env` so the script queries…

utils-fix-permissions

Fix file permissions on a directory tree on an HPC cluster (Leonardo, Jupiter, TACC, etc.) so other users can read your shared data, conda envs, or work directories. Runs `scripts/permissions/fix_permissions.sh <dir>` over SSH on the target cluster — sets…

utils-reclaim-stale-snapshots

Reclaim idle Daytona SNAPSHOTS org-wide to free space under the 60-snapshot cap, using scripts/daytona/daytona_snapshot_manager.py. Deletes only harbor__ per- environment snapshots idle past the standing threshold GT'd in .agents/projects/daytona/daytona.md —…

write-tests

Write or revise tests with an emphasis on behavior, regression coverage, pytest style, and avoiding "slop tests." Use when adding tests, fixing failing tests, reviewing test quality, or deciding what test would catch a bug.

writing-style

Marin house writing style. Use when drafting or revising Marin-authored prose, including commit messages and GitHub PR, issue, or comment text.