start.sh: LOW_MEM=1 short-circuits to status server only (kill all bg daemons)

start.sh: fix repo clone paths arkashira/* → axentx/* (5 silent 404s)

start.sh: gate 5 heavy harvest launchers behind LOW_MEM

perf(harvest): bump worker fleet 1→16 + push cadence 2× — use the headroom

feat(rounds-7-12-clean-no-tokens): SHARD + ZeroGPU + personae + monitor

feat(burst-but-dont-die): adaptive auto-scaler + tighter discoverer cycle

fix(oom-permanent): memory guard + redis cap + heavy-task gating

fix(oom): stagger cron offsets + STREAM=1 — minute=0 burst was OOM trigger

feat(regress-cron): daily 11:00 UTC regression-test on both Space + anchor

fix(low-mem): prune daemon stack — Space OOM after Round 9+10 added too much

feat(round10-continuous): always-on multi-source crawler + tight worker idle

feat(round8-trillion): 207 sources + streaming worker + enrich pipeline + dual-mode mirror

fix(start): LOW_MEM mode for cpu-basic — Space dead 7h on OOM

feat(v2-round5): sustainability loops + 2026 techniques

feat(bulk-mirror): 100+ massive datasets + 4-worker claim-queue coordination

fix(audit-2026-04-29): throttle gh-actions-ticker 60s→600s + harden /data symlink recreation

fix(boot): disable train-ready-pusher at Space boot — caused RUNTIME_ERROR; script preserved for manual launch

feat(train-ready): single-file pusher train-ready/latest.jsonl.gz for CDN-only training fetches — eliminates HF API listing during Lightning/Kaggle training

feat: dataset-mirror — 100x faster ingest by bulk-cloning community SFT mixes

feat: 3-track training pipeline — Kaggle T4 + Lightning H200 + (Modal pending)

trigger: kaggle-trainer on every boot + cron 90-min (was 6-hr)

feat: kaggle-trainer + llm-burst x3 — TRAIN now, MAX synthesis

feat: expand-role-keywords daemon — LLM-expanded SDLC keywords

feat: llm-burst-generator daemon — synthesize 7K+ training pairs/day from 8 free LLM APIs

feat: gh-actions-ticker daemon — 60s burst dispatch (10x faster than cron)

feat: self-heal-watchdog + drop shards 6→4 to dodge OOM kill

fix: dedup.db corruption was crashing all 16 ingest shards

fix: REMOVE Mac dependency + boost HF Space to 16 shards + parquet-direct

feat: caps 5x bump (94M\u2192293M) + parallel 4-shard bulk ingest

feat: RAG fully wired \u2014 FTS5 + vector hybrid retrieval, no train needed for now

feat: CONTINUOUS auto-orchestrate (4 parallel workers, no 20-min gaps)

fix: trigger enrich on boot + 7 trillion-scale corpora + cron 4h\u219260min

feat: HF dataset agentic discoverer \u2014 never-ending mega-mix hunt

feat: central dedup store \u2014 single source of truth across ALL writers

feat: 12 mega-mixes (69 \u2192 80 datasets) — pre-curated 4.8M pairs cap

feat: GitHub agentic crawler — maximize 4-PAT pool (20K req/h aggregate)

feat: integrate 11 new datasets + Granite + threat-intel + SRE postmortem daemons

fix: 3 critical issues — dataset privacy, crawler pollution, offset reset

fix: unblock 5-hour stall + close self-improvement loop + MoA + synthetic data

feat: full SDLC domain expert system + 5 SWE datasets + 4 models + HF Inference Providers

fix: include HF_TOKEN in secret loading + explicit token pass to HfApi

fix: clone axentx repos from arkashira/* (correct GH path), include workio + hermes-toolbelt

feat: migrate $HOME/.claude/* to $HOME/.surrogate/* (clean separation from Claude Code)

feat: parallel orchestrate + agentic crawler + skill synthesis + 3-min sync

fix: orchestrate pipeline + PRD wizard + continuous scrape

Add research-loop + dataset-enrich + 6h+30m cron schedule on HF

SECURITY: set +x BEFORE secret loop (was after) + remove later set -x re-enable

SECURITY: disable set -x before .env source + verify uvicorn deps before exec

Add set -x boot trace to find hang point

Non-blocking git clones + GIT_TERMINAL_PROMPT=0 + 30s timeout