Add automatic native profile closure ladder runner (sprint 250)

docs/constructive_editing_runtime_plan.md

@@ -150,7 +150,7 @@ Parallel planning tranche (active):
   - `logs/taskitem_runs/TEST_ONLY_spec_planning_baseline_20260226/deterministic_spec_readiness.json`
 
 Planning runtime controls (active):
-- `sprint232_plan.md` to `sprint249_plan.md`
+- `sprint232_plan.md` to `sprint250_plan.md`
 - semantic bridge + intake augmentation + requirement injection + expansion gating are wired into:
   - `tools/mcp/run_sprint_taskitem_pipeline.sh`
 - current policy default is native-first semantic fallback:
@@ -202,3 +202,5 @@ Planning runtime controls (active):
   - `WSTONE_NATIVE_RAW_CANDIDATE_MAX_VARIANTS`
   - `WSTONE_NATIVE_RAW_CANDIDATE_REQUIRE_UPLIFT`
   - `tools/mcp/score_native_tasks_profile_coverage.py`
+- closure ladder can select the minimal passing strategy automatically:
+  - `tools/mcp/run_native_profile_closure_ladder.sh`

docs/generator_readiness_gap_registry_2026-02-26.md

@@ -47,7 +47,7 @@ This is the canonical dated registry for "not production-ready" generator gaps.
 | GR-018 | Performance/security/rollout constrained refactor enforcement gap | `docs/gap_hunt_fullstack_multifile_2026-02-26.md`, `logs/taskitem_runs/challenging_fullstack_multifile_20260226_r5/results.jsonl` | `partial` | Hard checks now enforce migration rollback + data-loss policy, security deny-by-default, SLO p95 presence, and rollout staged+abort policy. Enforcement is contract-level; generator capability under these constraints is still weak in C++ AB path. | Constraint-aware generation follow-up |
 | GR-019 | Parity-blocked readiness load (gating without capability closure) | `logs/taskitem_runs/challenging_fullstack_multifile_20260226_r7/summary.json`, `logs/taskitem_runs/challenging_subset_prod_20260226_r7/summary.json`, `docs/sprint225_227_execution_tracker_2026-02-26.md` | `partial` | Sprint 225-227 reduced blocked parity load from `6` to `0` on both tracked hard catalogs while keeping unresolved divergence at `0`. This closes immediate safety debt for current corpora, but robustness is still contingent on pattern-driven repair classes. | Generalize repairs beyond queue-shaped transpile outputs |
 | GR-020 | Semantic fallback overuse masks weak native decomposition | `logs/taskitem_runs/TEST_ONLY_sprint236_semantic_fallback_audit_20260226/semantic_fallback_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint237_semantic_fallback_gate_fail_20260226/semantic_fallback_budget_gate.json`, `logs/taskitem_runs/TEST_ONLY_sprint238_native_gate_fail_20260226.json`, `logs/taskitem_runs/TEST_ONLY_sprint239_semantic_fallback_audit_20260226/semantic_fallback_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint240_retry_20260226_145631/00_summary.json`, `docs/sprint236_execution_tracker_2026-02-26.md`, `docs/sprint237_execution_tracker_2026-02-26.md`, `docs/sprint238_execution_tracker_2026-02-26.md`, `docs/sprint239_execution_tracker_2026-02-26.md`, `docs/sprint240_execution_tracker_2026-02-26.md` | `partial` | Sprint 236 added deterministic fallback-gap auditing with tool + constraint metadata. Sprint 237 added fallback-budget hard gate (`max-fallback-rate`) and produced expected fail/pass artifacts. Sprint 238 added native decomposition hard gate in pipeline (`min task count`, `min semantic signal count`) so weak native generation can be blocked before fallback masking. Sprint 239 added native reason enrichment and improved semantic signal density (`0 -> 6`). Sprint 240 added native decomposition retry with explicit minimum-task policy; on current sample retry attempted but did not improve depth (`2 -> 2`). | Native decomposition task-depth upgrade (increase native task granularity beyond 2) |
-| GR-021 | Impact-specific native decomposition coverage not enforced uniformly | `docs/native_decomposition_impact_list_2026-02-26.md`, `tools/mcp/profiles/native_decomposition_impact_profiles.json`, `logs/taskitem_runs/TEST_ONLY_sprint241_fullstack_impact_20260226_150416/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint241_native_impact_aggregate_20260226/native_impact_coverage_aggregate.json`, `logs/taskitem_runs/TEST_ONLY_sprint242_impact_remediation_loop_20260226/remediation_loop_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint243_impact_remediation_tasks_loop_20260226_r2/remediation_loop_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_20260226_151651/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_enforce_20260226_151709/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint245_intrinsic_20260226_151835/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint246_multishot_20260226_153033/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint246_multishot_enforce_20260226_153045/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint247_singleshot_20260226_153230/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint247_singleshot_enforce_20260226_153241/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint248_rawsearch_20260226_153903/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint249_rawguard_20260226_154028/02ae_raw_candidate_search.json` | `partial` | Sprint 241 introduced impact profiles/gates; 242-243 remediation loops; 244 first-pass autofill; 245 intrinsic constraints only (no uplift); 246 multishot closes hard sample; 247 single-shot shaping closes with multishot+autofill disabled; 248 raw candidate search over 8 variants found no uplift (`selected_variant=0`, `7 -> 7`); 249 added no-uplift guardrail to hard-fail ineffective raw search attempts. Residual gap remains in raw generator single-shot quality without overlays. | Improve raw single-shot generator output so profile closure does not rely on shaping/multishot/autofill overlays |
+| GR-021 | Impact-specific native decomposition coverage not enforced uniformly | `docs/native_decomposition_impact_list_2026-02-26.md`, `tools/mcp/profiles/native_decomposition_impact_profiles.json`, `logs/taskitem_runs/TEST_ONLY_sprint241_fullstack_impact_20260226_150416/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint241_native_impact_aggregate_20260226/native_impact_coverage_aggregate.json`, `logs/taskitem_runs/TEST_ONLY_sprint242_impact_remediation_loop_20260226/remediation_loop_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint243_impact_remediation_tasks_loop_20260226_r2/remediation_loop_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_20260226_151651/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_enforce_20260226_151709/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint245_intrinsic_20260226_151835/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint246_multishot_20260226_153033/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint246_multishot_enforce_20260226_153045/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint247_singleshot_20260226_153230/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint247_singleshot_enforce_20260226_153241/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint248_rawsearch_20260226_153903/00_summary.json`, `logs/taskitem_runs/TEST_ONLY_sprint249_rawguard_20260226_154028/02ae_raw_candidate_search.json`, `logs/taskitem_runs/TEST_ONLY_sprint250_closure_ladder_20260226/closure_ladder_summary.json` | `partial` | Sprint 241 introduced impact profiles/gates; 242-243 remediation loops; 244 first-pass autofill; 245 intrinsic constraints only (no uplift); 246 multishot closes hard sample; 247 single-shot shaping closes with multishot+autofill disabled; 248 raw candidate search found no uplift; 249 added no-uplift guardrail; 250 added automatic closure ladder and selected `single_shot_shape` as minimal passing mode on hard sample. Residual gap remains in raw generator single-shot quality without overlays. | Improve raw single-shot generator output so profile closure does not rely on shaping/multishot/autofill overlays |
 
 ## What Was Covered Today (Sprints 175-184)
 

docs/progress_log_2026-02-26.md

@@ -323,3 +323,14 @@
 - Current measured result:
   - baseline `7`, best `7` failing profiles
   - run blocked correctly under require-uplift mode.
+
+## Sprint 250 Added (Same Day)
+
+- Added automatic closure ladder runner:
+  - `tools/mcp/run_native_profile_closure_ladder.sh`
+  - mode order: `raw_only -> single_shot_shape -> multishot -> autofill`
+- Dated artifact:
+  - `logs/taskitem_runs/TEST_ONLY_sprint250_closure_ladder_20260226/closure_ladder_summary.json`
+- Current measured result on hard fullstack sample:
+  - selected mode: `single_shot_shape`
+  - selected run passes impact coverage with `failing_profile_count=0`

docs/sprint250_execution_tracker_2026-02-26.md

@@ -0,0 +1,32 @@
+# Sprint 250 Execution Tracker - 2026-02-26
+
+## Scope
+- `sprint250_plan.md`
+
+## Implemented
+
+New runner:
+- `tools/mcp/run_native_profile_closure_ladder.sh`
+  - mode order:
+    1. `raw_only`
+    2. `single_shot_shape`
+    3. `multishot`
+    4. `autofill`
+  - runs each mode with enforced impact coverage gate.
+  - stops at first pass and records selected mode.
+  - writes deterministic summary:
+    - `closure_ladder_summary.json`
+
+## Validation Artifact
+
+- `logs/taskitem_runs/TEST_ONLY_sprint250_closure_ladder_20260226/closure_ladder_summary.json`
+
+Observed result on hard fullstack sample:
+- selected mode: `single_shot_shape`
+- selected run impact coverage:
+  - `status=ok`
+  - `failing_profile_count=0`
+
+## Explicit Completion Signal
+
+- Sprint 250: `DONE` (implemented + ladder selection verified)

editor/src/Sprint250IntegrationSummary.h

@@ -0,0 +1,6 @@
+#pragma once
+
+// Sprint 250 integration summary:
+// - Added automatic closure ladder runner for native profile coverage.
+// - Tries progressive strategies and selects the minimal passing mode.
+// - Emits deterministic summary with selected mode and run artifact path.

sprint250_plan.md

@@ -0,0 +1,11 @@
+# Sprint 250 Plan: Automatic Native Profile Closure Ladder
+
+## Goal
+Select the minimal legal closure strategy that passes enforced impact coverage for a given spec.
+
+## Steps
+- Step 2295: Add closure ladder runner for progressive strategy modes.
+- Step 2296: Encode mode order from least to most assistive.
+- Step 2297: Persist per-mode run logs and selected-mode summary.
+- Step 2298: Validate ladder on hard fullstack sample.
+- Step 2299: Add `Sprint250IntegrationSummary.h` and execution tracker.

tools/mcp/run_native_profile_closure_ladder.sh

@@ -0,0 +1,101 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
+SPEC_PATH="${1:-}"
+OUT_DIR="${2:-$ROOT_DIR/logs/taskitem_runs/TEST_ONLY_native_profile_closure_ladder_$(date +%Y%m%d_%H%M%S)}"
+if [[ -z "$SPEC_PATH" ]]; then
+  echo "usage: $0 <spec_path> [out_dir]" >&2
+  exit 2
+fi
+if [[ ! -f "$SPEC_PATH" ]]; then
+  echo "error: spec not found: $SPEC_PATH" >&2
+  exit 2
+fi
+mkdir -p "$OUT_DIR"
+
+run_mode() {
+  local mode="$1"
+  local logfile="$OUT_DIR/${mode}.log"
+  local rcfile="$OUT_DIR/${mode}.rc"
+
+  local env_common=(
+    WSTONE_NATIVE_IMPACT_COVERAGE_GATE=1
+    WSTONE_NATIVE_IMPACT_COVERAGE_ENFORCE=1
+    WSTONE_NATIVE_INTRINSIC_BOOST=1
+    WSTONE_NATIVE_RAW_CANDIDATE_SEARCH=0
+    WSTONE_NATIVE_RAW_CANDIDATE_REQUIRE_UPLIFT=0
+    WSTONE_NATIVE_SINGLESHOT_PROFILE_SHAPE=0
+    WSTONE_NATIVE_MULTISHOT_DECOMP=0
+    WSTONE_NATIVE_PROFILE_AUTOFILL=0
+  )
+
+  case "$mode" in
+    raw_only)
+      env_common+=(WSTONE_NATIVE_RAW_CANDIDATE_SEARCH=1)
+      ;;
+    single_shot_shape)
+      env_common+=(WSTONE_NATIVE_SINGLESHOT_PROFILE_SHAPE=1)
+      ;;
+    multishot)
+      env_common+=(WSTONE_NATIVE_MULTISHOT_DECOMP=1)
+      ;;
+    autofill)
+      env_common+=(WSTONE_NATIVE_PROFILE_AUTOFILL=1)
+      ;;
+    *)
+      echo "unknown mode: $mode" >&2
+      exit 3
+      ;;
+  esac
+
+  set +e
+  env "${env_common[@]}" "$ROOT_DIR/tools/mcp/run_sprint_taskitem_pipeline.sh" "$SPEC_PATH" >"$logfile" 2>&1
+  local rc=$?
+  set -e
+  echo "$rc" > "$rcfile"
+
+  local latest
+  latest=$(ls -1dt "$ROOT_DIR/logs/taskitem_runs/$(basename "$SPEC_PATH" .md)_"* | head -n1)
+  echo "$latest" > "$OUT_DIR/${mode}.run_dir"
+
+  if [[ "$rc" -eq 0 ]]; then
+    return 0
+  fi
+  return "$rc"
+}
+
+modes=(raw_only single_shot_shape multishot autofill)
+selected=""
+selected_run=""
+selected_rc=1
+
+for mode in "${modes[@]}"; do
+  if run_mode "$mode"; then
+    selected="$mode"
+    selected_run="$(cat "$OUT_DIR/${mode}.run_dir")"
+    selected_rc=0
+    break
+  fi
+done
+
+jq -n \
+  --arg spec "$SPEC_PATH" \
+  --arg out_dir "$OUT_DIR" \
+  --arg selected_mode "$selected" \
+  --arg selected_run "$selected_run" \
+  --argjson selected_rc "$selected_rc" \
+  --argjson attempted_modes "$(printf '%s\n' "${modes[@]}" | jq -R . | jq -s .)" \
+  '{
+    status: (if $selected_rc == 0 then "ok" else "fail" end),
+    spec:$spec,
+    out_dir:$out_dir,
+    attempted_modes:$attempted_modes,
+    selected_mode:$selected_mode,
+    selected_run:$selected_run,
+    selected_rc:$selected_rc
+  }' | tee "$OUT_DIR/closure_ladder_summary.json"
+
+if [[ "$selected_rc" -ne 0 ]]; then
+  exit 21
+fi