fix: recognize image input for GPT-6.2 models routed through ClawRouter When neither the selected endpoint nor the model row declares input, ClawRouter's fallback classified gpt-6.2-sol and gpt-6.2-astra as text-only. Add both upstream IDs and cover them in the fallback test.
Current
·
C2
·2026-11
fix: recognize image input for GPT-6.2 models routed through ClawRouter
Find Your Interest
- Everyone Hates AI. Half of Them Use It.
- Debunking AI agent accessibility claims and solving AI alignment for accessibility
- Would you trust an AI bot to find the fix for vulnerabilities in your code?
- The Roundup by ByteByteGo
- Why Accessibility Has Never Been More Profitable
- LWiAI Podcast #258 - Opus 5.5, Sol and Luna, Muse, DeepSeek-V4.1-Flash, Xi
- How Meta Built Forum With AI-Native Engineering
- The Guardrail Is Now Part of the Attack
- The Grid V3 coming soon?
- Developers, Your Next Customer Is an AI Agent
Current
·
C2
·2026-11






