tractor/ai/prompt-io/opencode
Gud Boi ba07e09d2a Model bindspaces as scoped capabilities
Separate serializable bindspace declarations from live namespace
identity, FDs, ownership and teardown resources.

Require child namespace entry during spawn bootstrap, before actor
runtime initialization, then distinguish listen/dial provisioning and
owned/borrowed cleanup without encoding operation role into maddrs.

Prompt-IO: ai/prompt-io/opencode/20260820T021516Z_dfad66a0_prompt_io.md

(this patch was generated in some part by `opencode` using `gpt-5.6-sol` (`openai`))
2026-08-19 22:31:56 -04:00
..
20260804T030309Z_65bf9df5_prompt_io.md Wait for ctx exit in `maybe_open_context()` 2026-08-03 23:45:42 -04:00
20260804T030309Z_65bf9df5_prompt_io.raw.md Wait for ctx exit in `maybe_open_context()` 2026-08-03 23:45:42 -04:00
20260818T021729Z_d9a6e2e9_prompt_io.md Add `TunnelledAddress` wrapper primitives 2026-08-18 02:01:30 -04:00
20260818T021729Z_d9a6e2e9_prompt_io.raw.md Add `TunnelledAddress` wrapper primitives 2026-08-18 02:01:30 -04:00
20260818T075031Z_dd02c7c0_prompt_io.md Support nested `wg` maddrs 2026-08-18 23:25:56 -04:00
20260818T075031Z_dd02c7c0_prompt_io.raw.md Support nested `wg` maddrs 2026-08-18 23:25:56 -04:00
20260819T213144Z_f81fc5e5_prompt_io.md Peel tunnels before `Channel` connects 2026-08-19 18:33:49 -04:00
20260819T213144Z_f81fc5e5_prompt_io.raw.md Peel tunnels before `Channel` connects 2026-08-19 18:33:49 -04:00
20260819T213145Z_f81fc5e5_prompt_io.md Peel tunnels before `Endpoint` binding 2026-08-19 21:30:10 -04:00
20260819T213145Z_f81fc5e5_prompt_io.raw.md Peel tunnels before `Endpoint` binding 2026-08-19 21:30:10 -04:00
20260820T021516Z_dfad66a0_prompt_io.md Model bindspaces as scoped capabilities 2026-08-19 22:31:56 -04:00
20260820T021516Z_dfad66a0_prompt_io.raw.md Model bindspaces as scoped capabilities 2026-08-19 22:31:56 -04:00
README.md Wait for ctx exit in `maybe_open_context()` 2026-08-03 23:45:42 -04:00

README.md

AI Prompt I/O Log - OpenCode

This directory tracks prompt inputs and model outputs for AI-assisted development using opencode.

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