tractor/ai/prompt-io/claude
Gud Boi b5b0504918 Add prompt-IO log for subint spawner design kickoff
Log the `claude-opus-4-7` design session that produced the phased plan
(A: modularize `_spawn`, B: `_subint` backend, C: harness) and concrete
Phase A file-split for #379. Substantive bc the plan directly drives
upcoming impl.

Prompt-IO: ai/prompt-io/claude/20260417T034918Z_9703210_prompt_io.md

(this commit msg was generated in some part by [`claude-code`][claude-code-gh])
[claude-code-gh]: https://github.com/anthropics/claude-code
2026-04-17 16:48:22 -04:00
..
20260406T172848Z_02b2ef1_prompt_io.md Add per-`ctx_key` isolation tests for `maybe_open_context()` 2026-04-06 14:37:47 -04:00
20260406T193125Z_85f9c5d_prompt_io.md Add xfail test for `_Cache.run_ctx` teardown race 2026-04-06 18:17:04 -04:00
20260406T222648Z_f086222_prompt_io.md Add prompt-io log for `run_ctx` teardown analysis 2026-04-09 14:42:42 -04:00
20260406T222648Z_f086222_prompt_io.raw.md Condense `.raw.md` prompt-IO logs, add `diff_cmd` refs 2026-04-16 17:44:14 -04:00
20260413T192116Z_f851f28_prompt_io.md Add `test_tpt_bind_addrs.py` + fix type-mixing bug 2026-04-14 19:54:14 -04:00
20260413T205048Z_269d939c_prompt_io.md Add `parse_endpoints()` to `_multiaddr` 2026-04-14 19:54:14 -04:00
20260413T205048Z_269d939c_prompt_io.raw.md Condense `.raw.md` prompt-IO logs, add `diff_cmd` refs 2026-04-16 17:44:14 -04:00
20260414T163300Z_befedc49_prompt_io.md Add `prefer_addr()` transport selection to `_api` 2026-04-14 19:54:14 -04:00
20260414T163300Z_befedc49_prompt_io.raw.md Condense `.raw.md` prompt-IO logs, add `diff_cmd` refs 2026-04-16 17:44:14 -04:00
20260417T034918Z_9703210_prompt_io.md Add prompt-IO log for subint spawner design kickoff 2026-04-17 16:48:22 -04:00
20260417T034918Z_9703210_prompt_io.raw.md Add prompt-IO log for subint spawner design kickoff 2026-04-17 16:48:22 -04:00
README.md Add per-`ctx_key` isolation tests for `maybe_open_context()` 2026-04-06 14:37:47 -04:00

README.md

AI Prompt I/O Log — claude

This directory tracks prompt inputs and model outputs for AI-assisted development using claude (Claude Code).

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.md files)

Usage

Entries are created by the /prompt-io skill or automatically via /commit-msg integration.

Human contributors remain accountable for all code decisions. AI-generated content is never presented as human-authored work.