cc-os/openspec/changes/archive/2026-06-04-incremental-migration-and-reference-benchmark/tasks.md

1. Record the decision

• 1.1 Add ADR-013 to docs/memory-system/03-architecture-decisions.md recording the build-order inversion (vault-migration-first → build-first / migrate-incrementally), with rationale and rejected alternatives
• 1.2 Update the "Decisions locked" pointer in CLAUDE.md to reference ADR-013

2. Author the benchmark prompt deliverable

• 2.1 Choose and create the home for the prompt and per-model reference outputs (default docs/memory-system/benchmark/)
• 2.2 Write the shared minimal extraction spec (entities, typed relationships, INFERRED/AMBIGUOUS confidence) as the schema the subagents must emit
• 2.3 Write the copy/paste-able dispatch prompt file: one subagent per Claude tier (claude-haiku-4-5, claude-sonnet-4-6, claude-opus-4-8), fairness contract (note text + spec only; no repo/project context), per-model output files
• 2.4 Confirm the prompt embeds the output schema verbatim and names the fixture inputs and per-model output paths

3. Rewrite Step 2c (benchmark) in the runbook

• 3.1 Replace Step 2c's model table/metrics with the reference-set design: Claude tiers only, quality-only metrics, speed deferred to the later Ollama run
• 3.2 State that the per-model reference set is the rubric local Ollama models are scored against later, and point to the prompt file
• 3.3 Update Open question §6 to reflect that the Claude reference run produces references (not the final model choice)

4. Resequence Step 1 (migration) in the runbook

• 4.1 Rewrite Step 1 so bulk vault migration is deferred; keep only fixture-note selection (5–10 notes, deliberate variety) as the pre-build step
• 4.2 Add the post-build sequence: validate end-to-end on one small mixed code+docs project, then onboard projects one at a time with observe-and-adjust between each
• 4.3 Make the four distinct items explicit in the runbook: benchmark fixtures / deferred bulk migration / initial mixed validation project / project-by-project rollout
• 4.4 Note the migration-unit granularity question and that vault notes (SLM path) and project code (tree-sitter path) are different extraction paths

5. Reconcile and verify

• 5.1 Check docs/memory-system/04-build-plan.md for any statement of the old "migration first" order and reconcile it with ADR-013
• 5.2 Update the _Last updated:_ / status lines on every edited design doc
• 5.3 Re-read the edited runbook end-to-end to confirm Step 1 and Step 2c are internally consistent and the four distinct items are not blurred