A specific free model was retired and good-night generation failed outright, because the fallback branch had never executed.
The fallback chain sat unused after I wrote it. Then that free model was retired, good-night generation failed outright, and the fallback branch broke the first time it actually ran.
Now I drill it regularly: point the primary model at an address that doesn’t exist and check that requests land on the backup by themselves.
Written byShihao Qi
Related
The Synthetic Set Picked C. Forty-Four Real Questions Picked B.2026-10-27A synthetic evaluation set gave a clean answer to what granularity memory should be stored at. Real questions from real chats gave a different one — and along the way turned up three measurement problems.#Memory#Evaluation#Measurement#LLMWhere the Prefix-Cache Hits Went2026-10-27The hit rate dropped, and the total alone couldn’t say why. Looked at in 128-token blocks, the losses came from one section placed in the wrong spot, and from two providers with completely different caching rules.#LLM#Cost#ObservabilityWhy the More You Write a Persona, the Less Human It Sounds2026-10-21The persona grew from 800 to 8,000 characters, and replies started sounding like the character reciting its own spec. Most of the problems turned out to be in the code that assembles the prompt, not in the persona text itself.#Prompt#Persona#LLM