Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions docs/BACKLOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -4275,6 +4275,10 @@ systems. This track claims the space.

## P2 — research-grade

- [ ] **Git-native PR-conversation preservation — extract PR review threads + comments to git-tracked files on merge.** Aaron 2026-04-24 Otto-113 directive: *"you probably need to resolve and save the conversations on the PRs to git for gitnative presevration"*. Currently PR review threads (Copilot / Codex connector / human reviewer comments) live GitHub-side only; if repo is mirrored / forked / GitHub has an outage / repo is migrated, the conversation substrate is lost. For glass-halo transparency + retractability, PR discussions belong in-repo. Proposed mechanism: workflow (or post-merge skill) that fetches all review threads + general PR comments for a merged PR, serialises them as markdown at `docs/pr-discussions/PR-<number>-<slug>.md` with attribution (reviewer id/bot), timestamps, thread structure, and resolution status. Scope: (1) design PR-discussion schema + file shape; (2) fetch-on-merge mechanism (GHA workflow using `gh api graphql`); (3) privacy pass (strip anything sensitive from reviewer comments); (4) backfill historical PRs or declare cutover-forward. Priority P2 research-grade; effort S (mechanism) + M (backfill if chosen). Composes with Otto-113 bootstrap-attempt-1 memory + docs-lint/memory-no-lint policy (discussions go in docs/) + the ChatGPT-download-skill (PR #300) pattern.
Copy link

Copilot AI Apr 24, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The phrase "reviewer id/bot" conflicts with the repo’s terminology rule to use “agent” rather than “bot” (see docs/CONFLICT-RESOLUTION.md:229-232). Consider rewording to something like “reviewer identity/agent type” while keeping the same meaning.

Suggested change
- [ ] **Git-native PR-conversation preservation — extract PR review threads + comments to git-tracked files on merge.** Aaron 2026-04-24 Otto-113 directive: *"you probably need to resolve and save the conversations on the PRs to git for gitnative presevration"*. Currently PR review threads (Copilot / Codex connector / human reviewer comments) live GitHub-side only; if repo is mirrored / forked / GitHub has an outage / repo is migrated, the conversation substrate is lost. For glass-halo transparency + retractability, PR discussions belong in-repo. Proposed mechanism: workflow (or post-merge skill) that fetches all review threads + general PR comments for a merged PR, serialises them as markdown at `docs/pr-discussions/PR-<number>-<slug>.md` with attribution (reviewer id/bot), timestamps, thread structure, and resolution status. Scope: (1) design PR-discussion schema + file shape; (2) fetch-on-merge mechanism (GHA workflow using `gh api graphql`); (3) privacy pass (strip anything sensitive from reviewer comments); (4) backfill historical PRs or declare cutover-forward. Priority P2 research-grade; effort S (mechanism) + M (backfill if chosen). Composes with Otto-113 bootstrap-attempt-1 memory + docs-lint/memory-no-lint policy (discussions go in docs/) + the ChatGPT-download-skill (PR #300) pattern.
- [ ] **Git-native PR-conversation preservation — extract PR review threads + comments to git-tracked files on merge.** Aaron 2026-04-24 Otto-113 directive: *"you probably need to resolve and save the conversations on the PRs to git for gitnative presevration"*. Currently PR review threads (Copilot / Codex connector / human reviewer comments) live GitHub-side only; if repo is mirrored / forked / GitHub has an outage / repo is migrated, the conversation substrate is lost. For glass-halo transparency + retractability, PR discussions belong in-repo. Proposed mechanism: workflow (or post-merge skill) that fetches all review threads + general PR comments for a merged PR, serialises them as markdown at `docs/pr-discussions/PR-<number>-<slug>.md` with attribution (reviewer identity/agent type), timestamps, thread structure, and resolution status. Scope: (1) design PR-discussion schema + file shape; (2) fetch-on-merge mechanism (GHA workflow using `gh api graphql`); (3) privacy pass (strip anything sensitive from reviewer comments); (4) backfill historical PRs or declare cutover-forward. Priority P2 research-grade; effort S (mechanism) + M (backfill if chosen). Composes with Otto-113 bootstrap-attempt-1 memory + docs-lint/memory-no-lint policy (discussions go in docs/) + the ChatGPT-download-skill (PR #300) pattern.

Copilot uses AI. Check for mistakes.
Copy link

Copilot AI Apr 24, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

“docs-lint/memory-no-lint policy” is referenced here but doesn’t appear to be defined or documented anywhere else in the repo. This makes the backlog item hard to interpret later; consider either linking to the canonical doc/workflow that defines this policy or rephrasing to reference the actual mechanism by file path.

Suggested change
- [ ] **Git-native PR-conversation preservation — extract PR review threads + comments to git-tracked files on merge.** Aaron 2026-04-24 Otto-113 directive: *"you probably need to resolve and save the conversations on the PRs to git for gitnative presevration"*. Currently PR review threads (Copilot / Codex connector / human reviewer comments) live GitHub-side only; if repo is mirrored / forked / GitHub has an outage / repo is migrated, the conversation substrate is lost. For glass-halo transparency + retractability, PR discussions belong in-repo. Proposed mechanism: workflow (or post-merge skill) that fetches all review threads + general PR comments for a merged PR, serialises them as markdown at `docs/pr-discussions/PR-<number>-<slug>.md` with attribution (reviewer id/bot), timestamps, thread structure, and resolution status. Scope: (1) design PR-discussion schema + file shape; (2) fetch-on-merge mechanism (GHA workflow using `gh api graphql`); (3) privacy pass (strip anything sensitive from reviewer comments); (4) backfill historical PRs or declare cutover-forward. Priority P2 research-grade; effort S (mechanism) + M (backfill if chosen). Composes with Otto-113 bootstrap-attempt-1 memory + docs-lint/memory-no-lint policy (discussions go in docs/) + the ChatGPT-download-skill (PR #300) pattern.
- [ ] **Git-native PR-conversation preservation — extract PR review threads + comments to git-tracked files on merge.** Aaron 2026-04-24 Otto-113 directive: *"you probably need to resolve and save the conversations on the PRs to git for gitnative presevration"*. Currently PR review threads (Copilot / Codex connector / human reviewer comments) live GitHub-side only; if repo is mirrored / forked / GitHub has an outage / repo is migrated, the conversation substrate is lost. For glass-halo transparency + retractability, PR discussions belong in-repo. Proposed mechanism: workflow (or post-merge skill) that fetches all review threads + general PR comments for a merged PR, serialises them as markdown at `docs/pr-discussions/PR-<number>-<slug>.md` with attribution (reviewer id/bot), timestamps, thread structure, and resolution status. Scope: (1) design PR-discussion schema + file shape; (2) fetch-on-merge mechanism (GHA workflow using `gh api graphql`); (3) privacy pass (strip anything sensitive from reviewer comments); (4) backfill historical PRs or declare cutover-forward. Priority P2 research-grade; effort S (mechanism) + M (backfill if chosen). Composes with Otto-113 bootstrap-attempt-1 memory + storing preserved discussions under `docs/pr-discussions/` (so they live in `docs/`, not `memory/`) + the ChatGPT-download-skill (PR #300) pattern.

Copilot uses AI. Check for mistakes.

- [ ] **Ongoing memory-sync mechanism — keep in-repo `memory/` mirrored with auto-memory writes during each Otto tick.** Aaron 2026-04-24 Otto-113 directive *"our memories should all be checked in now"* + Otto-114 confirmation that in-repo memory/ is the natural home for ALL memory types. Otto-113 one-shot sync (PR #307) mirrored 439 files. Going forward, every Otto tick that writes to `~/.claude/projects/.../memory/` should also land new/updated files in-repo `memory/` with matching MEMORY.md pointer update (per memory-index-integrity + memory-reference-existence-lint workflows). Proposed mechanisms: (a) end-of-tick skill that rsyncs new memories to a branch + PRs them; (b) direct-to-repo writes with auto-memory as read-cache; (c) GHA cron periodic sync. Initial preference: (a) for CLI-tool compatibility today, (b) long-term. Also includes path-unification design (decide whether to deprecate the `~/.claude/projects/...` path for this project entirely or keep as staging). Priority P2 research-grade; effort S (rsync skill) + M (direct-write tooling). Composes with `memory/feedback_natural_home_of_memories_is_in_repo_now_all_types_*.md` (Otto-114 policy) + PR #307 one-shot sync + memory-index-integrity workflow.
Copy link

Copilot AI Apr 24, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The backlog row references memory/feedback_natural_home_of_memories_is_in_repo_now_all_types_*.md, but there’s no matching file under memory/. To keep the reference trail accurate, point this to an existing memory/doc that states the in-repo-memory policy (e.g., memory/README.md) or remove the path until the policy memory exists.

Suggested change
- [ ] **Ongoing memory-sync mechanism — keep in-repo `memory/` mirrored with auto-memory writes during each Otto tick.** Aaron 2026-04-24 Otto-113 directive *"our memories should all be checked in now"* + Otto-114 confirmation that in-repo memory/ is the natural home for ALL memory types. Otto-113 one-shot sync (PR #307) mirrored 439 files. Going forward, every Otto tick that writes to `~/.claude/projects/.../memory/` should also land new/updated files in-repo `memory/` with matching MEMORY.md pointer update (per memory-index-integrity + memory-reference-existence-lint workflows). Proposed mechanisms: (a) end-of-tick skill that rsyncs new memories to a branch + PRs them; (b) direct-to-repo writes with auto-memory as read-cache; (c) GHA cron periodic sync. Initial preference: (a) for CLI-tool compatibility today, (b) long-term. Also includes path-unification design (decide whether to deprecate the `~/.claude/projects/...` path for this project entirely or keep as staging). Priority P2 research-grade; effort S (rsync skill) + M (direct-write tooling). Composes with `memory/feedback_natural_home_of_memories_is_in_repo_now_all_types_*.md` (Otto-114 policy) + PR #307 one-shot sync + memory-index-integrity workflow.
- [ ] **Ongoing memory-sync mechanism — keep in-repo `memory/` mirrored with auto-memory writes during each Otto tick.** Aaron 2026-04-24 Otto-113 directive *"our memories should all be checked in now"* + Otto-114 confirmation that in-repo memory/ is the natural home for ALL memory types. Otto-113 one-shot sync (PR #307) mirrored 439 files. Going forward, every Otto tick that writes to `~/.claude/projects/.../memory/` should also land new/updated files in-repo `memory/` with matching MEMORY.md pointer update (per memory-index-integrity + memory-reference-existence-lint workflows). Proposed mechanisms: (a) end-of-tick skill that rsyncs new memories to a branch + PRs them; (b) direct-to-repo writes with auto-memory as read-cache; (c) GHA cron periodic sync. Initial preference: (a) for CLI-tool compatibility today, (b) long-term. Also includes path-unification design (decide whether to deprecate the `~/.claude/projects/...` path for this project entirely or keep as staging). Priority P2 research-grade; effort S (rsync skill) + M (direct-write tooling). Composes with `memory/README.md` (in-repo memory policy) + PR #307 one-shot sync + memory-index-integrity workflow.

Copilot uses AI. Check for mistakes.

- [ ] **Frontier plugin inventory + in-source discipline — catalogue the plugins Zeta's factory needs for the Frontier UI + substrate (both `.claude-plugin/` and `.codex-plugin/`), restructure around the new skill-vs-plugin best practices, and enforce that all plugins land in-source rather than in harness-local sandboxes.** Aaron 2026-04-24 Otto-103 directive: *"we should backlog what plugins we need for frontier, seems like a big opportunity to restruture for new best practices and everyting else, we also wanna make sure our plugins are making it into source and not some harness sandbox. backlog."*

**Context.** After session restart Aaron flagged five Codex built-in skills (Image Gen / OpenAI Docs / Plugin Creator / Skill Creator / Skill Installer) + asked Otto to figure out skills-vs-plugins distinction. Otto-103 research (PR #290, `docs/research/codex-builtins-skills-vs-plugins-factory-integration-2026-04-24.md`) established: **plugin = distribution/installation unit (JSON manifest + bundle); skill = single capability unit (SKILL.md)**. Plugins are containers; skills are contents. This row goes further — catalogue what plugins the factory itself needs.
Expand Down
Loading