Rate Limit Management Enhancements

This cluster focuses on improvements and fixes related to rate limit handling and cooldown mechanisms within the AI agent framework.

17 PRs

fix Representative: #14824

#	Title	Author	Created	GitHub
6781	feat(antigravity): proactive quota exhaustion detection	mealai	2026-02-02	View
7941	fix: scope rate-limit cooldowns per-model instead of per-provider	adrrr	2026-02-03	View
11371	Auth: cap rate-limit cooldown at 5 minutes; add maxCooldownMinutes config (#1...	lailoo	2026-02-07	View
13928	Classify session lock timeouts separately and improve lock diagnostics	kirillsaven	2026-02-11	View
14290	feat: x402 payment info parsing and configurable billing recovery [AI]	stubbi	2026-02-11	View
14574	fix: gentler rate-limit cooldown backoff + clear stale cooldowns on restart	JamesEBall	2026-02-12	View
14824	fix: do not trigger provider cooldown on LLM request timeouts rep	CyberSinister	2026-02-12	View
14914	fix: resolve actual failure reason for cooldown-skipped providers	mcaxtr	2026-02-12	View
16797	fix(auth-profiles): implement per-model rate limit cooldown tracking	mulhamna	2026-02-15	View
18902	fix: exempt format errors from auth profile cooldown	tag-assistant	2026-02-17	View
19267	fix: derive failover reason from timedOut flag to prevent unknown cooldown ca...	austenstone	2026-02-17	View
19926	fix: Extract status code from error messages for empty 429 responses	gaurav10gg	2026-02-18	View
20911	fix: auto-reset session when all models time out	tag-assistant	2026-02-19	View
20946	fix: skip auth cooldown on timeout (not an auth failure)	austenstone	2026-02-19	View
23210	fix: avoid cooldown on timeout/unknown failovers	nydamon	2026-02-22	View
23341	feat: prioritize lastGood auth profile over round-robin ordering	kevin930321	2026-02-22	View
23564	feat(auth): add timeout retry before auth profile rotation	echoVic	2026-02-22	View