piker/ai/prompt-io
Gud Boi 0d2c88ce3e Repair IB startup gaps in `ShmArray`
Keep reverse history and stored SHM layout aligned so sparse IB
frames do not expose permanent zero-time reservations.

Deats,
- omit inclusive query endpoints from SHM but retain full storage
- serialize and bound farm resets, blanks, and cancellations
- run the final null sweep after reverse retrieval completes
- require valid timestamp boundaries for synthetic gap rows
- cover the live QQQ 653-row failure and reset interleavings

Prompt-IO: ai/prompt-io/opencode/20260729T204046Z_ad6c560f_prompt_io.md

(this patch was generated in some part by `opencode` using `gpt-5.6-sol` (`openai`))
2026-11-11 18:35:47 -05:00
..
claude .ib.broker: lazily qualify contracts on order req 2026-11-09 17:05:43 -05:00
opencode Repair IB startup gaps in `ShmArray` 2026-11-11 18:35:47 -05:00
20261007T165453Z_bde2457b_prompt_io.md Fix endpoint config and daemon startup from PR94 review 2026-10-10 14:20:52 -04:00
20261007T165453Z_bde2457b_prompt_io.raw.md Fix endpoint config and daemon startup from PR94 review 2026-10-10 14:20:52 -04:00
20261010T232852Z_1fa45dfa_prompt_io.md Use `tractor`'s reviewed address-unpacking branch 2026-10-11 00:43:06 -04:00
20261010T232852Z_1fa45dfa_prompt_io.raw.md Use `tractor`'s reviewed address-unpacking branch 2026-10-11 00:43:06 -04:00
20261106T185628Z_495c0915_215e9b_prompt_io.md Contain provider failures during SHM gap repair 2026-11-06 15:20:58 -05:00
20261106T185628Z_495c0915_215e9b_prompt_io.raw.md Contain provider failures during SHM gap repair 2026-11-06 15:20:58 -05:00
20261106T201746Z_495c0915_612dfc_prompt_io.md Pin qualified `tractor` and require `trio>=0.34.0` 2026-11-06 15:21:33 -05:00
20261106T201746Z_495c0915_612dfc_prompt_io.raw.md Pin qualified `tractor` and require `trio>=0.34.0` 2026-11-06 15:21:33 -05:00
README.md Contain provider failures during SHM gap repair 2026-11-06 15:20:58 -05:00

README.md

AI Prompt I/O Log

This directory records substantive AI-assisted changes, prompts, original harness identity, and unedited outputs. Human contributors remain accountable for code decisions.

Records follow the NLNet generative AI policy. Each structured entry links its immutable .raw.md partner. Code output uses Git diff references to avoid duplication.