diff --git a/NEXT_AGENT_NOTES.md b/NEXT_AGENT_NOTES.md index f227893..ca40c02 100644 --- a/NEXT_AGENT_NOTES.md +++ b/NEXT_AGENT_NOTES.md @@ -2,6 +2,11 @@ ## Current Canonical State (2026-02-26) +- `TEST_ONLY` artifact rule: + - Any path under `logs/taskitem_runs/TEST_ONLY_*` is validation-only data. + - Do not use hardened specs in `TEST_ONLY_*` as source-of-truth project specs. + - See `logs/taskitem_runs/TEST_ONLY_README_2026-02-26.md`. + - Read first: - `docs/progress_log_2026-02-26.md` - `docs/generator_readiness_gap_registry_2026-02-26.md` diff --git a/docs/constructive_editing_runtime_plan.md b/docs/constructive_editing_runtime_plan.md index e6e0b89..09b88c8 100644 --- a/docs/constructive_editing_runtime_plan.md +++ b/docs/constructive_editing_runtime_plan.md @@ -146,5 +146,5 @@ Start Phase A: Parallel planning tranche (active): - `sprint228_plan.md` to `sprint231_plan.md` - baseline artifacts: - - `logs/taskitem_runs/spec_planning_baseline_20260226/fullstack_spec_readiness.json` - - `logs/taskitem_runs/spec_planning_baseline_20260226/deterministic_spec_readiness.json` + - `logs/taskitem_runs/TEST_ONLY_spec_planning_baseline_20260226/fullstack_spec_readiness.json` + - `logs/taskitem_runs/TEST_ONLY_spec_planning_baseline_20260226/deterministic_spec_readiness.json` diff --git a/docs/progress_log_2026-02-26.md b/docs/progress_log_2026-02-26.md index 3fb7820..d71b44c 100644 --- a/docs/progress_log_2026-02-26.md +++ b/docs/progress_log_2026-02-26.md @@ -72,3 +72,6 @@ - example product meta specs (10) - Batch report: - `docs/spec_hardening_batch_report_2026-02-26.md` +- Artifact isolation update: + - moved planning/hardening outputs to `logs/taskitem_runs/TEST_ONLY_*` paths. + - wrapper default now writes to `TEST_ONLY_spec_hardening_gate_*`. diff --git a/docs/spec_hardening_batch_report_2026-02-26.md b/docs/spec_hardening_batch_report_2026-02-26.md index d8dc45d..db433b1 100644 --- a/docs/spec_hardening_batch_report_2026-02-26.md +++ b/docs/spec_hardening_batch_report_2026-02-26.md @@ -12,13 +12,13 @@ Corpora: ## Batch Artifacts Drive batch: -- `logs/taskitem_runs/drive_spec_hardening_batch_20260226/results.jsonl` -- `logs/taskitem_runs/drive_spec_hardening_batch_20260226/summary.json` -- `logs/taskitem_runs/drive_spec_hardening_batch_20260226/quality_summary.json` +- `logs/taskitem_runs/TEST_ONLY_drive_spec_hardening_batch_20260226/results.jsonl` +- `logs/taskitem_runs/TEST_ONLY_drive_spec_hardening_batch_20260226/summary.json` +- `logs/taskitem_runs/TEST_ONLY_drive_spec_hardening_batch_20260226/quality_summary.json` Example project meta batch: -- `logs/taskitem_runs/example_projectmeta_hardening_batch_20260226/results.jsonl` -- `logs/taskitem_runs/example_projectmeta_hardening_batch_20260226/summary.json` +- `logs/taskitem_runs/TEST_ONLY_example_projectmeta_hardening_batch_20260226/results.jsonl` +- `logs/taskitem_runs/TEST_ONLY_example_projectmeta_hardening_batch_20260226/summary.json` ## High-Density Outcomes diff --git a/docs/spec_planning_baseline_2026-02-26.md b/docs/spec_planning_baseline_2026-02-26.md index 8dfee45..5d11b38 100644 --- a/docs/spec_planning_baseline_2026-02-26.md +++ b/docs/spec_planning_baseline_2026-02-26.md @@ -1,8 +1,8 @@ # Spec Planning Baseline - 2026-02-26 Run artifacts: -- `logs/taskitem_runs/spec_planning_baseline_20260226/fullstack_spec_readiness.json` -- `logs/taskitem_runs/spec_planning_baseline_20260226/deterministic_spec_readiness.json` +- `logs/taskitem_runs/TEST_ONLY_spec_planning_baseline_20260226/fullstack_spec_readiness.json` +- `logs/taskitem_runs/TEST_ONLY_spec_planning_baseline_20260226/deterministic_spec_readiness.json` ## Results diff --git a/docs/sprint228_231_execution_tracker_2026-02-26.md b/docs/sprint228_231_execution_tracker_2026-02-26.md index 46f2e10..5764c4d 100644 --- a/docs/sprint228_231_execution_tracker_2026-02-26.md +++ b/docs/sprint228_231_execution_tracker_2026-02-26.md @@ -25,12 +25,12 @@ Planned and started: ## Baseline Evidence -- `logs/taskitem_runs/spec_planning_baseline_20260226/fullstack_spec_readiness.json` -- `logs/taskitem_runs/spec_planning_baseline_20260226/deterministic_spec_readiness.json` -- `logs/taskitem_runs/spec_planning_hardening_20260226/sprint228_before.json` -- `logs/taskitem_runs/spec_planning_hardening_20260226/sprint228_after.json` -- `logs/taskitem_runs/spec_planning_hardening_20260226/sprint228_hardened.md` -- `logs/taskitem_runs/spec_hardening_gate_20260226_s228_r2/report.json` +- `logs/taskitem_runs/TEST_ONLY_spec_planning_baseline_20260226/fullstack_spec_readiness.json` +- `logs/taskitem_runs/TEST_ONLY_spec_planning_baseline_20260226/deterministic_spec_readiness.json` +- `logs/taskitem_runs/TEST_ONLY_spec_planning_hardening_20260226/sprint228_before.json` +- `logs/taskitem_runs/TEST_ONLY_spec_planning_hardening_20260226/sprint228_after.json` +- `logs/taskitem_runs/TEST_ONLY_spec_planning_hardening_20260226/sprint228_hardened.md` +- `logs/taskitem_runs/TEST_ONLY_spec_hardening_gate_20260226_s228_r2/report.json` Observed baseline: - both sample docs currently return `needs_spec_hardening` @@ -49,7 +49,7 @@ Pipeline hard-gate proof: Reusable flow wrapper: - `tools/mcp/run_spec_hardening_gate.sh` - example invocation: - - `tools/mcp/run_spec_hardening_gate.sh sprint228_plan.md logs/taskitem_runs/spec_hardening_gate_20260226_s228_r2` + - `tools/mcp/run_spec_hardening_gate.sh sprint228_plan.md logs/taskitem_runs/TEST_ONLY_spec_hardening_gate_20260226_s228_r2` ## Explicit Completion Signal diff --git a/docs/stale_log_manifest_2026-02-26.md b/docs/stale_log_manifest_2026-02-26.md index e1512ee..ecabe52 100644 --- a/docs/stale_log_manifest_2026-02-26.md +++ b/docs/stale_log_manifest_2026-02-26.md @@ -29,3 +29,8 @@ These are useful for history but should not be treated as current execution trut ## Rule For Next Agents When docs disagree, trust newest dated execution tracker + run artifacts under `logs/taskitem_runs/`. + +## Test-Only Artifact Rule + +- Treat directories under `logs/taskitem_runs/TEST_ONLY_*` as validation artifacts only. +- Never treat markdown specs generated within `TEST_ONLY_*` directories as authoritative product specs. diff --git a/tools/mcp/run_spec_hardening_gate.sh b/tools/mcp/run_spec_hardening_gate.sh index 3e76d38..3ab23ae 100755 --- a/tools/mcp/run_spec_hardening_gate.sh +++ b/tools/mcp/run_spec_hardening_gate.sh @@ -3,7 +3,7 @@ set -euo pipefail ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)" SPEC_INPUT="${1:?usage: run_spec_hardening_gate.sh [out_dir]}" -OUT_DIR="${2:-$ROOT_DIR/logs/taskitem_runs/spec_hardening_gate_$(date +%Y%m%d_%H%M%S)}" +OUT_DIR="${2:-$ROOT_DIR/logs/taskitem_runs/TEST_ONLY_spec_hardening_gate_$(date +%Y%m%d_%H%M%S)}" MIN_SCORE="${WSTONE_SPEC_READINESS_MIN_SCORE:-65}" RUN_PIPELINE="${WSTONE_SPEC_HARDENING_RUN_PIPELINE:-1}"