bill/whetstone_DSL
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add first-pass profile autofill closure path (sprint 244)

Browse Source
This commit is contained in:
Bill
2026-02-26 15:17:56 -07:00
parent 050fee9480
commit b68f7edc84
8 changed files with 261 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/constructive_editing_runtime_plan.md
View File

@@ -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 `sprint243_plan.md`
- `sprint232_plan.md` to `sprint244_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:
@@ -181,3 +181,7 @@ Planning runtime controls (active):
- remediation loop can also synthesize and inject profile-specific task bundles:
- `WSTONE_EXTRA_TASKS_FILE`
- `tools/mcp/synthesize_native_impact_remediation_tasks.py`
- first-pass pipeline can synthesize profile autofill task bundles without external loop:
- `WSTONE_NATIVE_PROFILE_AUTOFILL`
- `WSTONE_NATIVE_PROFILE_AUTOFILL_MAX_TASKS`
- `tools/mcp/synthesize_native_profile_autofill_tasks.py`

2
docs/generator_readiness_gap_registry_2026-02-26.md
View File

@@ -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` | `partial` | Sprint 241 added one-by-one impact profiles and a pipeline-integrated native impact coverage gate (`native_impact_coverage`). Sprint 242 added profile-driven remediation synthesis and rerun loop. Sprint 243 added profile-specific remediation task bundle synthesis + injection and updated coverage checking over effective task set; hard fullstack sample now closes in one rerun (`failing_profile_count 7 -> 0`). Native first-pass generator depth remains weak, so closure currently depends on remediation injection path. | Improve first-pass native generator decomposition so coverage passes without remediation injection |
| 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` | `partial` | Sprint 241 added one-by-one impact profiles and native impact coverage gate. Sprint 242-243 added remediation synthesis and task-bundle closure loop (`7 -> 0` in one rerun on hard sample). Sprint 244 added first-pass profile autofill in the main pipeline; hard fullstack sample now passes impact coverage in first pass with autofill enabled (`failing_profile_count=0`), and enforced gate fails when autofill is disabled (`failing_profile_count=7`). Remaining gap is intrinsic native generator depth without scaffolding assistance. | Improve intrinsic first-pass native decomposition quality so profile closure does not rely on synthetic autofill tasks |
## What Was Covered Today (Sprints 175-184)

14
docs/progress_log_2026-02-26.md
View File

@@ -234,3 +234,17 @@
- `logs/taskitem_runs/TEST_ONLY_sprint243_impact_remediation_tasks_loop_20260226_r2/remediation_loop_summary.json`
- Current measured loop result on hard fullstack sample:
- `failing_profile_count 7 -> 0`
## Sprint 244 Added (Same Day)
- Added first-pass profile autofill in main pipeline:
- `tools/mcp/synthesize_native_profile_autofill_tasks.py`
- `WSTONE_NATIVE_PROFILE_AUTOFILL`
- `WSTONE_NATIVE_PROFILE_AUTOFILL_MAX_TASKS`
- summary packet: `native_profile_autofill`
- Autofill now closes impact coverage inside first-pass generation on hard fullstack sample:
- ON: `failing_profile_count=0`
- OFF: `failing_profile_count=7`
- Enforced gate behavior verified:
- pass with autofill ON: `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_enforce_20260226_151709/00_summary.json`
- fail with autofill OFF: `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_enforce_20260226_151710/06_native_impact_coverage.json`

40
docs/sprint244_execution_tracker_2026-02-26.md Normal file
View File

@@ -0,0 +1,40 @@
# Sprint 244 Execution Tracker - 2026-02-26
## Scope
- `sprint244_plan.md`
## Implemented
New first-pass autofill tool:
- `tools/mcp/synthesize_native_profile_autofill_tasks.py`
- Detects active impact profiles from spec.
- Evaluates missing coverage against current native tasks.
- Synthesizes profile-specific autofill task bundles.
Pipeline integration in `tools/mcp/run_sprint_taskitem_pipeline.sh`:
- Added controls:
- `WSTONE_NATIVE_PROFILE_AUTOFILL` (default `0`)
- `WSTONE_NATIVE_PROFILE_AUTOFILL_MAX_TASKS` (default `12`)
- Autofill runs before native impact coverage gate and can inject tasks directly.
- Autofill task injection is reflected in `extra_tasks` and summary packet:
- `native_profile_autofill`
## Validation Artifacts
A/B with coverage gate (non-enforced):
- autofill ON:
- `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_20260226_151651/00_summary.json`
- coverage: `failing_profile_count=0`
- autofill OFF:
- `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_20260226_151652/00_summary.json`
- coverage: `failing_profile_count=7`
Enforced gate behavior:
- pass with autofill ON:
- `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_enforce_20260226_151709/00_summary.json`
- fail with autofill OFF:
- `logs/taskitem_runs/TEST_ONLY_sprint244_autofill_enforce_20260226_151710/06_native_impact_coverage.json`
## Explicit Completion Signal
- Sprint 244: `DONE` (implemented + enforced pass/fail behavior verified)