cleanup: remove version debug logging

debug: try pkg_resources to get litellm version

debug: print litellm version on startup

fix: skip model-catalog loading in proxy_app to avoid cpu-basic hang

fix: restore model-catalog + render-config with usable-models filter (191 models)

fix: handle missing upstream in models_response, add env to skip litellm remote startup

fix: start proxy_app immediately, let litellm boot in background

debug: add python import test, cat full log instead of tail

debug: extend wait to 120s, tail litellm log every 10s

debug: capture litellm stdout+stderr to log file

debug: add litellm version check and config dump

fix: remove stderr redirect, add litellm health wait

fix: skip huge catalog, use static config only, skip proxy_app startup render

use static minimal config, skip render-config entirely

handle string usable_model_ids (space-separated)

fix log path to /tmp/verify.log

add debug logging to startup script

simplify startup: remove render-config, start with minimal config only

bulletproof startup with minimal config fallback

fix: deduplicate models (one entry per model ID)

fix: match usable models by suffix (handles provider prefix mismatch)

feat: enable usable models filter by default

feat: filter catalog to usable models only (auto-fetches from HF dataset)

fix: wait for litellm upstream readiness before starting proxy

fix: detect domain_email secrets in startup wait

fix: map service_domain_email HF secrets to expected env vars

force rebuild: bust Docker cache v2

force rebuild: bust Docker cache

load all 3 probe results: chat_usable, image_usable, vision_usable

add /admin/discover/results endpoint

fix: upload start-litellm.sh as binary to preserve LF

remove broken GitHub fetch, all scripts updated

full repo sync

update all scripts: /admin/discover, fix verify base_url

add 5min cooldown between probes, vision gets more retries

remove usable-models cache TTL, always fetch fresh from dataset

add --no-filter to image and vision probes for full coverage

add chat+image+vision probes to /admin/verify

rename Space to alchoholpad/litellm, update AGENTS.md URL

touch proxy_app.py to bust Docker COPY cache

touch start-litellm.sh to bust Docker COPY cache

fetch latest proxy_app.py from GitHub at startup, bypass Docker cache

fix: unbuffered python output for real-time probe logs

fix: add early log writes to debug probe startup

fix: stream probe logs line-by-line for real-time viewing

fix: use public URL for verify probe instead of internal port

fix: capture probe output to log file, show upload errors

add /admin/logs endpoint to read probe log in real time

fix: use asyncio subprocess to avoid blocking event loop

fetch usable-models from HF dataset, upload after probe