goodboy
/
tractor
1
0
Fork 2
Code Issues 5 Pull Requests 6 Packages Projects Releases Wiki Activity
tractor/ai/prompt-io
History
Gud Boi 9a0f220fd5 Fix built-in level names in `at_least_level()` 
The `CUSTOM_LEVELS`-only lookup raised `KeyError` for built-in
log levels such as 'INFO'. Resolve other registered names through
`logging.getLevelNamesMapping()` only when the custom lookup
misses, without eagerly evaluating the fallback on custom hits.

Deats,
- keep custom precedence, case-insensitive names and `NOTSET=0`;
- preserve integer inputs and unknown-name `KeyError` behavior;
- keep logger-local and global `isEnabledFor()` disable controls;
- advertise integer inputs on the adapter's `at_least_level()`;
- add 62 raw/adapted regressions with explicit threshold examples
  and fixture docs distinguishing instance and global log state.

The logging suite passed all 70 cases; the original Piker consumer
probe passed 8/8 with its string-level feed guard retained.

Prompt-IO: ai/prompt-io/20261011T053737Z_a966928d_prompt_io.md

(this patch was generated in some part by `opencode` using
`gpt-6.1-sol` (`openai`))
 		2026-10-16 20:31:49 -04:00
..
claude Pin tpt prompt provenance to immutable refs 2026-08-31 12:27:23 -04:00
opencode Emit canonical tagged addresses 2026-09-01 15:47:28 -04:00
prompts Add `tractor.to_actor` one-shot task API subpkg 2026-08-21 15:03:34 -04:00
20261011T053737Z_a966928d_prompt_io.md Fix built-in level names in `at_least_level()` 2026-10-16 20:31:49 -04:00
20261011T053737Z_a966928d_prompt_io.raw.md Fix built-in level names in `at_least_level()` 2026-10-16 20:31:49 -04:00
README.md Fix built-in level names in `at_least_level()` 2026-10-16 20:31:49 -04:00

README.md

AI Prompt I/O Log

This directory tracks prompt inputs and model outputs for AI-assisted development across harnesses.

Policy

Prompt logging follows the NLNet generative AI policy. All substantive AI contributions are logged with:

  • Original harness, and provider/model when known
  • 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.