Inside Daisy's Runtime Upgrade: Better Roles, Recovery, and Models
By DigiEntropy Engineering · 2026-07-18 · 10 min read
We studied a cross-vendor prompt corpus, copied none of it, rebuilt Daisy's provider boundary, retired deepseek-chat safely, and measured the result across 49 real engineering scenarios.
About this post — Authored by an AI assistant using DigiEntropy's polynomial corpus, the universal compressor predictor, and the project's chart-generation tooling. Charts are produced by Python scripts that read the same database the live site queries; tables and formulas are pulled from the same engineering modules. Findings reflect the project's current dataset and methodology — send corrections or deeper questions to admin@digientropy.com. The most useful lesson in a leaked system prompt is usually not the prose. It is the machinery around it: which message gets system priority, how tools describe themselves, when a recovery instruction appears, and what deterministic code refuses to leave to the model. We reviewed the cross-vendor system-prompts corpus maintained by asgeirtj as an untrusted pattern library. We copied no hidden prompt, policy, persona, or vendor-specific instruction into Daisy. Instead, we extracted four testable strategies, measured the model line before touching production, changed one layer at a time, and ran the same 49 engineering scenarios again. The result is a quieter but more important Daisy upgrade than a new button: GPT-5.2 is now the measured default, old deepseek-chat selections migrate safely to DeepSeek V4 Flash, system/user/tool roles survive the provider boundary, specialist answer rules arrive only after the relevant engine runs, and failed tools get one typed recovery path instead of a raw error string. The model deadline came first DeepSeek's official API documentation scheduled the legacy deepseek-chat and deepseek-reasoner aliases for retirement on 24 July 2026. That made the operational question urgent: which current model should replace them, and should DeepSeek still be Daisy's default? We answered with one unchanged-runtime comparison: 49 scenarios per model, every turn using the real Daisy loop and real DigiEntropy engines, judged by GPT-5.2 on routing, correctness, helpfulness, honesty, presentation, and project grounding. Quality alone did not settle it. V4 Pro was the slowest option by a wide margin, and V4 Flash was also slower than GPT-5.2 in this workload. The bubble chart makes the production choice plain. GPT-5.2 had the best quality, no fabrications, no fallbacks, and lower median latency than either current DeepSeek model. V4 Flash was the best DeepSeek option. V4 Pro cost latency without producing a quality lift. So Daisy's default changed to OpenAI / GPT-5.2. Users or plans that explicitly select DeepSeek now get DeepSeek V4 Flash. The provider list no longer offers the retired aliases, generic…