Inspect Parquet bytes directly without opening storage or normalizing malformed evidence. Deats, - report canonical schema, timestamp, index and finite-value state - retain exact cadence aggregates with bounded endpoint details - snapshot bytes before parsing and clean up partial copy failures - reject unsafe FQMEs, links, collisions and non-regular sources Prompt-IO: ai/prompt-io/opencode/20260728T005034Z_ed85721c_prompt_io.md (this patch was generated in some part by `opencode` using `gpt-5.6-sol` (`openai`)) |
||
|---|---|---|
| .. | ||
| 20260721T205228Z_58ffe487_prompt_io.md | ||
| 20260721T205228Z_58ffe487_prompt_io.raw.md | ||
| 20260721T215055Z_c6ec3d41_prompt_io.md | ||
| 20260721T215055Z_c6ec3d41_prompt_io.raw.md | ||
| 20260722T001357Z_16f3cd6f_prompt_io.md | ||
| 20260722T001357Z_16f3cd6f_prompt_io.raw.md | ||
| 20260722T001358Z_16f3cd6f_prompt_io.md | ||
| 20260722T001358Z_16f3cd6f_prompt_io.raw.md | ||
| 20260722T024133Z_3a4f6737_prompt_io.md | ||
| 20260722T024133Z_3a4f6737_prompt_io.raw.md | ||
| 20260722T024134Z_3a4f6737_prompt_io.md | ||
| 20260722T024134Z_3a4f6737_prompt_io.raw.md | ||
| 20260724T220156Z_43d7a3ed_prompt_io.md | ||
| 20260724T220156Z_43d7a3ed_prompt_io.raw.md | ||
| 20260727T204711Z_84a6d47b_prompt_io.md | ||
| 20260727T204711Z_84a6d47b_prompt_io.raw.md | ||
| 20260727T212454Z_689df816_prompt_io.md | ||
| 20260727T212454Z_689df816_prompt_io.raw.md | ||
| 20260727T215906Z_689df816_prompt_io.md | ||
| 20260727T215906Z_689df816_prompt_io.raw.md | ||
| 20260728T005034Z_ed85721c_prompt_io.md | ||
| 20260728T005034Z_ed85721c_prompt_io.raw.md | ||
| 20260728T232718Z_ed85721c_prompt_io.md | ||
| 20260728T232718Z_ed85721c_prompt_io.raw.md | ||
| README.md | ||
README.md
AI Prompt I/O Log - OpenCode
This directory tracks prompt inputs and model outputs for AI-assisted development using OpenCode.
Policy
Prompt logging follows the NLNet generative AI policy. Substantive AI contributions are logged with the model, timestamp, prompt, response, and affected files.
Usage
Entries are created by the prompt-io skill. Human contributors remain accountable for all code decisions; AI-generated content is not presented as human-authored work.