cleanup: remove version debug logging

debug: try pkg_resources to get litellm version

debug: print litellm version on startup

revert: use main-latest instead of pinned v1.90.0

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

pin litellm to v1.90.0, add missing deps, bulletproof startup

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

fix: use sync HTTP for dataset fetch

force rebuild: bust Docker cache

add /v1/usable-models endpoint, remove catalog mapping

map catalog names to upstream model names

load all 3 probe results: chat_usable, image_usable, vision_usable

rebuild catalog from discovered models

add /admin/discover/results endpoint

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

remove broken GitHub fetch, all scripts updated

fix: write_json_atomic not defined

full repo sync

bust Docker cache with APP_VERSION env

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

add /admin/discover endpoint, fix datetime import

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