tractor/ai/prompt-io/claude
Gud Boi da7e749b09 Add prompt-io log for `run_ctx` teardown analysis
Documents the diagnostic session tracing why
per-`ctx_key` locking alone doesn't close the
`_Cache.run_ctx` teardown race — the lock pops
in the exiting caller's task but resource cleanup
runs in the `run_ctx` task inside `service_tn`.

(this patch was generated in some part by [`claude-code`][claude-code-gh])
[claude-code-gh]: https://github.com/anthropics/claude-code
2026-04-06 18:37:14 -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 2026-04-06 18:37:14 -04:00
20260406T222648Z_f086222_prompt_io.raw.md Add prompt-io log for `run_ctx` teardown analysis 2026-04-06 18:37:14 -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.