pikers
/
piker
4
1
Fork 0
Code Issues 20 Pull Requests 13 Packages Projects Releases Wiki Activity
piker/ai/prompt-io
History
Gud Boi e815fd77cf Save draft Trend Calculus and Jev prototype 
Save the native FHLS recurrence, causal FSP publication, aligned
multi-timeframe evidence, Trio/HTTPX Jev worker and Qt pivot/regime
overlays as one draft snapshot.

Retain tests, research sources, Lua fixtures, runnable examples,
full license notices and prompt provenance. The latest reviewed
offline suite passed 253 tests with one unrelated actor case
excluded and one existing Tractor warning.

Defer behavioral commit splitting and upstream history integration.
Live Jev quality, provider-service wiring and Pine parity remain
follow-ups in Taken.

Prompt-IO: ai/prompt-io/codex/20261005T050218Z_eed58566_trend_sampler_5d9102_prompt_io.md
Prompt-IO: ai/prompt-io/codex/20261005T041132Z_eed58566_trend_b4fe4d_prompt_io.md
Prompt-IO: ai/prompt-io/codex/20261005T054014Z_eed58566_trend_style_e3216f_prompt_io.md

(this patch was generated in some part by `codex` using
GPT-6 family models (`openai`); exact model IDs unavailable)
 		2026-10-06 16:04:41 -04:00
..
claude .ib.broker: lazily qualify contracts on order req 2026-06-10 17:36:51 -04:00
codex Save draft Trend Calculus and Jev prototype 2026-10-06 16:04:41 -04:00
opencode Raise on IB socket disconnects in proxy and trades 2026-09-17 18:24:17 -04:00
README.md Save draft Trend Calculus and Jev prototype 2026-10-06 16:04:41 -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. Substantive contributions record the original harness, provider/model when known, timestamps, the prompting sequence, and an unedited .raw.md partner.

Usage

Entries are created by the prompt-io skill or its commit-message integration. Harness-specific records live in their corresponding subdirectories. Code records can reference the associated Git diff instead of duplicating source code.

Human contributors retain responsibility for review and acceptance. AI-generated content is not presented as human-authored work.