Once `pformat_caller_frame()` renders successfully, the default `_mk_send_mte()` path still fails while formatting the valid IPC msg spec and then constructs its error message as a one-element tuple. Pass `MsgCodec` to `pformat_msgspec()`, keep the assembled message a string and exercise the complete path through a printable `MsgTypeError` regression. Prompt-IO: ai/prompt-io/opencode/20260820T150250Z_9afda1c6_prompt_io.md (this patch was generated in some part by `opencode` using `gpt-5.6-sol` (`openai`)) |
||
|---|---|---|
| .. | ||
| 20260804T030309Z_65bf9df5_prompt_io.md | ||
| 20260804T030309Z_65bf9df5_prompt_io.raw.md | ||
| 20260817T231825Z_359fe75c_prompt_io.md | ||
| 20260817T231825Z_359fe75c_prompt_io.raw.md | ||
| 20260820T150250Z_9afda1c6_prompt_io.md | ||
| 20260820T150250Z_9afda1c6_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. All substantive AI contributions are logged with:
- Model name and version
- Timestamps
- The prompts that produced the output
- Unedited model output (
.raw.mdfiles)
Usage
Entries are created by the prompt-io workflow. Human contributors remain accountable for all decisions. AI-generated content is never presented as human-authored work.