Make manual assignment evidence reproducible

Author: mchwang

AGENTS.md

@@ -47,5 +47,6 @@ Every reproduced race requires a failing-before and passing-after regression. As
 - In evidence records, label cited commits as baselines, intermediate checkpoints, or validated heads. Keep final exact-head results in a place that can name the resulting commit, such as the PR body or CI record.
 - Reproduce summary-only review concerns or turn them into a concrete follow-up issue. Do not repeatedly patch vague wording without a failure case.
 - A validation fixture for a summary-only concern must assert the disputed intermediate representation or state before using a downstream outcome as evidence that the concern was exercised.
+- Manual assignment evidence must include a reproducible per-segment manifest with stable choice ID, path, operation, assigned item, and final scope; aggregate counts alone are insufficient.
 - For each review round, record what changed, what was declined and why, and the regression evidence. Re-request review until a round returns no new findings.
 - Treat review-lesson extraction as a merge gate. Before invoking merge, classify every review finding in the PR body as: covered by an existing rule (cite it), captured by a new rule in this branch (cite it), or one-off (record why). Do not merge until this audit is complete and every required `AGENTS.md` update is included in the reviewed head. Omit rules that merely repeat existing guidance.

docs/experiments/manual-assignment.json

@@ -0,0 +1,18 @@
+{
+  "base": "5a2685cc709ca8f9f384e35e4d733012c7290d69",
+  "head": "442147d1bc9a33edeca1a605c9de3ada13f397f1",
+  "segments": [
+    { "choice_id": "96c76cee6518b177f272d8dba1f8db83314d0c09b62f036c6d6f41de40227d5c", "kind": "text", "operation": "+", "path": "AGENTS.md", "before_row": "Unplanned", "item": "P4", "scope": "in-scope" },
+    { "choice_id": "6000e022cb5f2c7fb602ba9dbd6b590cdf0672b1bdc984c036bf563423a86afd", "kind": "text", "operation": "+", "path": "AGENTS.md", "before_row": "Unplanned", "item": "P4", "scope": "in-scope" },
+    { "choice_id": "aa5dbe642c11d5f5f6f1630c0f979006b8e0e3182da3e0aeee8485fa997784d1", "kind": "file", "operation": null, "path": "docs/experiments/review-summary-edge-cases.md", "before_row": "Unplanned", "item": "P3", "scope": "in-scope" },
+    { "choice_id": "dfcf7097d83b6d55df0e4959f111370a96976b1c25f327e9d51838fc8224ceaf", "kind": "text", "operation": "+", "path": "docs/experiments/review-summary-edge-cases.md", "before_row": "Unplanned", "item": "P3", "scope": "in-scope" },
+    { "choice_id": "7a5227f9a6be94d6c16d1ea058ae3a5d956a5b53f93333a15d3b778222a90218", "kind": "text", "operation": "-", "path": "test/plant.test.ts", "before_row": "Unplanned", "item": "P2", "scope": "in-scope" },
+    { "choice_id": "142cf07bee22dbe7cf281b0d97efa49f9a502fed62701de8ec0c94500a94c788", "kind": "text", "operation": "+", "path": "test/plant.test.ts", "before_row": "Unplanned", "item": "P2", "scope": "in-scope" },
+    { "choice_id": "36cb67aa87587c9159f19ce0bac78a4d67f1348f55108f99e1fed99e5273a414", "kind": "text", "operation": "+", "path": "test/plant.test.ts", "before_row": "Unplanned", "item": "P2", "scope": "in-scope" },
+    { "choice_id": "88fada2e5b9a307f6db4fa6ccdbbf9e5bfbf00f26cbcacb33ac5bc141d74b85e", "kind": "text", "operation": "+", "path": "test/plant.test.ts", "before_row": "Unplanned", "item": "P2", "scope": "in-scope" },
+    { "choice_id": "9f010f7ae66fd80d72c5d78d45d4effbcdac76ebb6dfadc4efd4e66ac4af9f86", "kind": "text", "operation": "-", "path": "test/review.test.ts", "before_row": "Unplanned", "item": "P1", "scope": "in-scope" },
+    { "choice_id": "987cbec380909ee199bbe4df04a7d700c6f2a1f284c52f08120c159f8e92c35d", "kind": "text", "operation": "+", "path": "test/review.test.ts", "before_row": "Unplanned", "item": "P1", "scope": "in-scope" },
+    { "choice_id": "6b276597aa7294f44e5a549e38d423876266fe6a9a502bb5be089db2223a8976", "kind": "text", "operation": "+", "path": "test/review.test.ts", "before_row": "Unplanned", "item": "P1", "scope": "in-scope" },
+    { "choice_id": "c9379939cb69513a37cbb385440217283975294a2f8b340839d5f9d09ea126df", "kind": "text", "operation": "+", "path": "test/review.test.ts", "before_row": "Unplanned", "item": "P1", "scope": "in-scope" }
+  ]
+}

docs/experiments/manual-assignment.md

@@ -16,4 +16,4 @@ This prerequisite exercise uses real issue [#10](https://github.com/codeabovelab
 
 Codeboost exposed 12 segments before assignment, all in the Unplanned row. Each segment mapped to exactly one item through that item's declared file contract. After the assignments, the per-item segment counts were 4, 4, 2, and 2; all four rows reported `✓ Attributed` and `✓ In scope`. No segment was unclear or multiply owned, so this exercise produced no ambiguity fixture. The earlier rename and literal-path concerns already have focused fixtures in `test/review.test.ts` and `test/plant.test.ts`.
 
-The assignment was rerun from a detached worktree at the exact head using a fresh SQLite review store. The stored choices, rather than a hand-written diff classification alone, produced the final attribution and scope results above.
+The assignment was rerun from a detached worktree at the exact head using a fresh SQLite review store. The stored choices, rather than a hand-written diff classification alone, produced the final attribution and scope results above. `manual-assignment.json` records every stable choice ID with its kind, operation, path, original row, assigned item, and final scope so the 12 assignments can be checked individually.

docs/experiments/review-summary-edge-cases.md

@@ -22,4 +22,4 @@ Result: no defect reproduced. The summary supplied no expected color, state toke
 
 ## Gate result
 
-All three concerns are resolved as validated behavior. No issue supplied a failing case that justified a production patch. Issue #3's manual assignment and paired human go/no-go experiment remain pending and must use the frozen protocol in `review-protocol.md`.
+All three concerns are resolved as validated behavior. No issue supplied a failing case that justified a production patch. Issue #3's manual assignment is recorded in `manual-assignment.md`; its paired human go/no-go experiment remains pending and must use the frozen protocol in `review-protocol.md`.

docs/implementation/read-only-review.md

@@ -22,7 +22,7 @@ Store schema v2 adds the review counter and per-item notes through a transaction
 
 - No agent answers, test execution, AI findings ingestion, send-to-agent action, or merge control is included. These belong after the go/no-go gate. Four checks distinguish unavailable evidence from success.
 - File cards show mode/path/object IDs and blob byte sizes. PNG/JPEG/GIF/WebP previews are bounded to 1 MiB each and 4 MiB across a history; unsupported/oversized images say unavailable. Gitlink byte sizes are not applicable. SVG/HTML is never embedded.
-- The protocol at `docs/experiments/review-protocol.md` must be filled with the real pairs and committed before the first timed review. The manual assignment, real paired PRs, human timing, and final result are pending. Do not mark issue #3 closed or claim the gate passed.
+- The real issue pairs are frozen in `docs/experiments/review-protocol.md`, and the completed manual assignment is recorded in `docs/experiments/manual-assignment.md`. The paired PRs, exact review revision, human timing, and final result remain pending. Do not mark issue #3 closed or claim the gate passed.
 - The planting helper is intentionally limited to disposable clones and supported regular top-level paths; it never publishes PRs.
 
 ## Validation