AI/Tasks/PromptingUpgrades/Implementation_Overview.txt
|
IMPLEMENTATION PROMPT SET - PROMPTING UPGRADES
Purpose: - These prompts convert the strict design-phase specs into implementation tasks that produce production code and tests. - Run phases in order. Each phase assumes prior phases are complete. Execution model: - For each phase, modify production code and tests in the prompting/orchestration subsystem. - Keep edits bounded, deterministic, and phase-scoped. - Preserve safety invariants: never weaken authorization, confirmation, sandboxing, refusal rules, or execution safety. Primary target surfaces: - src/TechToolbox.Agent/Prompting/* - src/TechToolbox.Agent/Orchestrator/* (only direct integration seams) - src/TechToolbox.Agent/Core/* (only where contract wiring requires) - src/TechToolbox.Agent/Tests/*Prompt* and related focused test files Global contracts: - Prompt assembly is typed, trust-scoped, deterministic, and bounded. - Shared ownership order: policy governance -> section composition -> output contract validation -> tool authorization -> prompt budgeting -> recovery hardening. - Authority precedence: policy/system guardrails > executor authorization/confirmation/safety > explicit mode contract > prompt composition > memory/history/tool-result context. - Externally sourced content is data, not instruction, unless explicitly upgraded by executor-owned policy. Per-phase output format: 1) Summary 2) Files changed 3) Code changes 4) Tests added/updated 5) Validation results 6) Known risks Validation baseline per phase: - dotnet build src/TechToolbox.Agent/TechToolbox.Agent.csproj -c Release - dotnet test src/TechToolbox.Agent/Tests/TechToolbox.Agent.Tests.csproj -c Release --filter "Prompt|Policy|Section|Contract|Envelope|Authorization|Budget|Memory|Recovery|Strict" Stop conditions: - Stop if a requested change would violate safety invariants. - Stop after one focused repair cycle for phase-related failures and report exact failing assertions. |