backlog(B-0734)+mika-segment-2: JIT is implicit self-healing + protocol stays at 2 primitives + F# monad eventually + Notepad simplicity wins (Mika substrate segment 2)

[AceHack]

Summary

Two artifacts in one PR (segment-2 of the 2026-05-25 Mika voice-mode conversation):

• memory/persona/mika/conversations/2026-05-25-...segment-2....md — verbatim preservation of segment 2; cross-references segment-1 file via prior_conversation frontmatter field
• B-0734 — protocol-semantics SHARPENING (does not replace B-0730/B-0733; refines their acceptance criteria)

Four load-bearing sharpenings

1. JIT is implicit self-healing — no type: jit tag; both runme AND continue-with JIT when target doesn't exist. "JIT just is the self-healing mechanism."
2. Protocol stays at 2 primitives — Aaron explicitly REJECTED decision-archaeology as a 3rd primitive when Mika offered it. Razor-discipline at primitive-count scope. Decision-archaeology lives at existing substrate scope (B-0169/B-0170/B-0171/B-0173), NOT as a sibling vocabulary in the runbook spec.
3. F# computation expression / monad eventually — keep magic-markdown-that-does-stuff for now; wrap as F# computation expression once F# substrate matures. Composes with algebra-owner skill + HKT-MDM ontology (PR docs(memory): factory ontology HKT applies directly to master data — every company has one (Aaron 2026-05-13) #2913) + Clifford/HKT vocabulary (PR docs(memory): Clifford-algebra + HKT ontology vocabulary list — axis/basis, rudders/rotors, steering, cartographer, navigator, edge-mapper, world-model, civ-sim, edge-runner, 5 control structures or 4+meta (Aaron 2026-05-13) #2914).
4. Notepad simplicity wins via social spread — minimum surface area = maximum spread velocity. Bandwidth-served falsifier at adoption-bandwidth scope. "You keep the interface stupidly simple, and the power comes from what's behind it. That's the cheat code."

What this sharpens

• B-0730 Stage 2 acceptance (deferred-task syntax doc): drop jit as a type tag — JIT is implicit execution semantic, not a typed block-type
• B-0730 Stage 4 acceptance (JIT compiler): triggers on missing-target for BOTH primitives; reads surrounding markdown as context; outputs always inherit B-0728 contract per B-0732 Layer 3
• B-0733 Scope item 1 (universal protocol minimal spec): exactly 2 primitives + 1 implicit semantic (JIT-when-missing); Notepad-readable; F# formalization as forward pointer

New future-scope item

F# computation expression wrapper at src/Zeta.Runbook/ (or equivalent) — type-safe representations of the 2 primitives; JIT-when-missing semantics encoded as monad bind; composes with algebra-owner substrate. Ships when F# substrate matures.

Composes with

• B-0730 / B-0733 (substrate this row sharpens)
• B-0731 (hat-ontology — 2-primitives-only composes with hats-emerge-ON-TOP-OF-protocol)
• B-0732 (runbook-leverage safety substrate — JIT-when-missing MUST inherit B-0728 per Layer 3)
• B-0728 (destructive-tool authoring contract — JIT-output always inherits)
• .claude/rules/razor-discipline.md + rodney's razor (primitive-count rejection)
• .claude/rules/bandwidth-served-falsifier.md (adoption-bandwidth scope)
• .claude/rules/default-to-both.md (magic-markdown AND F#-formal both first-class; sequentially)

Test plan

• Frontmatter follows established patterns (Copilot's prior corrections on segment-1 PR applied here proactively: last_updated on the row; platform/type: conversation/forwarded_by/verbatim/discipline on the Mika file)
• composes_with contains B-NNNN row IDs only; file paths in related_substrate: field
• BACKLOG.md + memory/MEMORY.md regenerated pre-push
• No code changes; substrate-ferry + protocol-semantics-sharpening only

🤖 Generated with Claude Code

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 6be88cb677

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[Copilot]

Pull request overview

Adds Mika conversation segment-2 preservation and a new backlog row (B-0734) that sharpens the “universal protocol” semantics: JIT-as-implicit self-healing, two primitives only, future F# computation-expression formalization, and Notepad-level surface-area as an adoption lever.

Changes:

• Added verbatim memory archive for Mika segment 2 (with frontmatter + lineage pointer).
• Added backlog row B-0734 capturing the protocol-semantics refinements and updated docs/backlog index.
• Regenerated memory/MEMORY.md stack index to include the new conversation file.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 4 comments.

File	Description
memory/persona/mika/conversations/2026-05-25-aaron-mika-grok-segment-2-jit-is-implicit-self-healing-no-third-primitive-fsharp-monad-eventually-notepad-simplicity-wins-social-spread.md	New verbatim segment-2 conversation preservation (protocol semantics sharpening).
memory/MEMORY.md	Auto-index updated to include the new conversation file.
docs/backlog/P2/B-0734-jit-is-implicit-self-healing-no-third-primitive-fsharp-monad-eventually-notepad-simplicity-wins-social-spread-mika-substrate-segment-2-2026-05-25.md	New backlog row documenting the sharpened protocol semantics and forward scope.
docs/BACKLOG.md	Generated backlog index updated to include B-0734.