feat(code-review): in-process run-prefix segment runner + subprocess A/B parity oracle (PLN-1229 Phase 1)

Collapse the deterministic prefix (stages 01→cache_check) from one
orchestrator turn per stage into a single resumable process.

Production (code_review_helpers.py):
- cmd_run_prefix: reads run_plan.json + setup.json, resolves each stage's
  <ANGLE_BRACKET> tokens from prior-stage artifacts, dispatches cmd_* in-process
  with the stage's stdout redirect, honors on_failure + validation gates, and
  pauses at the genuine decision points — Gate A (hygiene_only), a PLN-725
  singleton needs_agent, or the Phase-1 boundary (stage_17_partition →
  ready_for_route). Resumable: the depends_on completed set is reconstructed
  from artifacts on disk, so each --resume-from segment is a fresh process.
- _execute_stage_inprocess mirrors the start.md Walker Contract steps 1-5;
  continue_with_coverage_gap emits a canonical agent-failure system finding.
- Registered run-prefix in config/cli.json (46th subparser).

Parity oracle (prefix_golden_harness.py + test_prefix_golden.py):
- Subprocess A-side (one python3 helpers.py <stage> per stage, real > redirect)
  vs B-side (python3 helpers.py run-prefix per segment). A and B implement the
  walk wrapper independently, so a shared wrapper bug cannot hide. Byte-equal
  (normalized) artifacts through cache_check across all 7 P0-B fixtures, plus a
  pause-sequence test pinning the resumable 3-segment contract.
- A failing gh stub shadows PATH so subprocess stages take the deterministic
  no-PR branch; env is snapshotted inside the hermetic HOME redirect.

P0-C contract tests (test_code_review_helpers.py, 31 tests): token resolution,
completed-set reconstruction, singleton needs_agent detection, on_failure
abort/continue incl. coverage-gap emission, and cmd_run_prefix error/boundary
returns.

SCHEMA.md §7b documents the run-prefix result contract. Zero orchestrator
changes (start.md untouched) — validated purely by the parity oracle. Route +
partition (Segment 3) fold in at Phase 2.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Author: wongk

plugins/code-review/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "code-review",
   "description": "Code review plugin",
-  "version": "3.1.1",
+  "version": "3.2.0",
   "author": {
     "name": "ClosedLoop",
     "email": "support@closedloop.ai"

plugins/code-review/SCHEMA.md

@@ -493,6 +493,49 @@ Stages from plans 01/03/05/06 are present in `run_plan.json` but marked
 
 ---
 
+## 7b. `run-prefix` result contract (PLN-1229)
+
+`run-prefix` runs the deterministic prefix (stages 01→`cache_check`) in ONE
+process instead of one orchestrator turn per stage. It reads `run_plan.json` +
+`setup.json` from `--cr-dir`, walks from `--resume-from` (default: the first
+plan stage), and stops at the next genuine decision point — emitting a status
+JSON (to stdout, or `--output <path>`) that tells the orchestrator what to do
+next. The runner is **resumable**: after handling a pause the orchestrator
+re-invokes `run-prefix --resume-from <resume_stage>`. Because each segment is a
+fresh process, the `depends_on` `completed` set is reconstructed from artifacts
+on disk (a prior stage counts as done iff its literal `expected_outputs` exist).
+
+**Result fields:**
+
+| Field           | Type            | Meaning                                                                 |
+| --------------- | --------------- | ----------------------------------------------------------------------- |
+| `next_action`   | string (enum)   | The pause reason — authoritative (read this, not the exit code).        |
+| `resume_stage`  | string \| null  | The stage id to pass as `--resume-from` on the next invocation.         |
+| `singleton`     | string \| null  | `"extract_signals"` \| `"coverage_critic"` when `needs_singleton`.      |
+| `failed_stage`  | string \| null  | The aborting stage id when `next_action == "error"`.                    |
+| `ran_stages`    | string[]        | Stage ids executed (or `continue`-failed) this segment, in order.       |
+| `message`       | string \| null  | Short diagnostic on `error`, else null.                                 |
+
+**`next_action` values:**
+
+| Value               | Fires at                              | Orchestrator does next                                                        |
+| ------------------- | ------------------------------------- | ---------------------------------------------------------------------------- |
+| `needs_singleton`   | `stage_11` / `stage_15` `needs_agent` | Spawn the `singleton` agent, write its output, re-invoke from `resume_stage`. |
+| `hygiene_exit`      | Gate A (`hygiene_only` after hygiene) | Present hygiene findings and stop (no verdict/footer).                        |
+| `ready_for_route`   | reaching `stage_17_partition`         | Run Gate B (`route`) + partition + the rest of the walk.                      |
+| `error`             | a stage aborted / a gate failed       | Fall back to the per-stage walk from `failed_stage`; partials are preserved.  |
+
+The exit code is `0` for every well-formed result (including `error`) — the
+`next_action` field is the contract. Route + partition (Segment 3) fold into the
+runner in Phase 2, at which point `ready_for_route` becomes `ready_for_reviewers`
+(carrying `fast_path` + `cache_status_message`). The `on_failure` policy of each
+stage is honored exactly as the Walker Contract prescribes: `abort` → `error`;
+`continue` → proceed; `continue_with_coverage_gap` → proceed after writing an
+`agent-failure` system finding to `agent_<stage>-failed.json` (collected by
+`collect-findings`).
+
+---
+
 ## 8. Determinism tiers (PLN-719 Section 8)
 
 | Tier                       | Definition                                                              | Required reviewers may depend? |