bill/whetstone_DSL
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
698 Commits 2 Branches 0 Tags
484d9e3f8c912974e871bb79118563179d552dc8
Commit Graph

698 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Bill
484d9e3f8c Sprint 64: Cost-Aware Transpilation Planning — Steps 869-878 
Adds cost modeling and budget enforcement for transpilation runs:
- PortingCostModel: LOC + ambiguity → compute/review/total cost + tier (step 869)
- ReviewEffortEstimator: ambiguity/risk → minutes + complexity label (step 870)
- ComputeCostEstimator: prior run history → avg duration/tokens (step 871)
- MultiPlanAlternativeGenerator: cheap/balanced/rigorous profiles (step 872)
- BudgetPolicyEnforcer: approve/requires_token/rejected decisions (step 873)
- CostQualityTradeoffReport: efficiency-based plan recommendation (step 874)
- whetstone_plan_transpilation_run MCP tool (step 875)
- whetstone_estimate_porting_cost MCP tool (step 876)
- CostTelemetryIntegration: cost error tracking + over-budget count (step 877)
- Sprint64IntegrationSummary (step 878)

All 10 steps passing (94 tests). Policy: over-budget plans require
explicit reviewer approval token.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-22 18:49:04 -07:00
Bill
00a9c4d976 Sprint 63: Learned Adapter Hints (Non-Authoritative) — Steps 859-868 
Implements the learned adapter hints layer with governance guardrails:
- HintFeatureExtractor: extract features from decision ledgers (step 859)
- HintModelInterface: pair-specific hint query interface (step 860)
- DeterministicFallback: safe fallback when hints unavailable (step 861)
- HintConfidencePacket: confidence bands and escalation logic (step 862)
- HintABHarness: A/B harness to measure hint effectiveness (step 863)
- HintRollbackControl: suppress and lift hint suppression per pair (step 864)
- whetstone_get_adapter_hints MCP tool (step 865)
- whetstone_set_hint_policy MCP tool (step 866)
- HintSafetyGuardrails: non-authoritative enforcement + audit (step 867)
- Sprint63IntegrationSummary (step 868)

All 10 steps passing (94 tests). Governance rule: learned hints may
suggest; deterministic policy decides.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-22 18:40:31 -07:00
Bill
457cbba44d Add Sprint 62: Adapter Quality Telemetry and Failure Taxonomy (Steps 849-858) 
All 86 tests passing across 10 steps.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-22 13:45:59 -07:00
Bill
160bfe33bd Add Sprints 60-61: Language Graduation and Certification Pipeline (Steps 829-848) 
Sprint 60: Language Graduation and Full-Matrix Release (Steps 829-838)
Sprint 61: Continuous Matrix Certification Pipeline (Steps 839-848)

All 90 tests passing across both sprints.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-22 13:38:25 -07:00
Bill
1696b92bb8 Add Sprints 46-59: governance, porting foundation, and language graduation prep (Steps 689-828) 
Sprints 46-58 implement the cross-language porting foundation: language-to-IR
adapters, equivalence checking, gate validation, legacy ingestion, managed/dynamic
families, low-level/logic-actor semantics, debug workflow tooling, AST-native
family tools, Rust/CPP raising tools, system-level orchestration, query family,
and porting gates. Sprint 59 adds the governance layer (policy packs, review
boards, waiver packets, ambiguity triage, decision ledger) with the
whetstone_review_porting_decision MCP tool.

Also includes: sprint plans 46-130, MCP taskitem pipeline scripts,
CLAUDE.md, docs, and full test matrix (steps 689-828).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-22 13:18:10 -07:00
Bill
84bdad8e9e Add Sprints 111-117: closed-loop iteration epoch 
Sprint 111: IterationSession context primitive
Sprint 112: EnvironmentSnapshot and diff
Sprint 113: Build output feedback loop
Sprint 114: Test failure feedback loop
Sprint 115: Requirements derivation from AST
Sprint 116: FeedbackLoopOrchestrator (wires 111-115)
Sprint 117: HiveMind integration (iteration steps as distributed jobs)

These sprints begin Epoch 3 — closed-loop determinism.
Sprints 1-110 made code generation open-loop deterministic.
Sprints 111+ make the full dev workflow (sense→act→observe→repeat)
structurally deterministic, with HiveMind as the execution layer.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-21 13:27:32 -07:00
BillTheMaker
b1d9cf6540 Add foundational governance concepts and core objectives 
Added foundational philosophy and governance concepts for the system, including Bayesian Constitutionalism and Epistemic Regularization. Outlined the core objective function and policy generation mechanisms.
 2026-02-21 09:11:38 -07:00
Bill
e683a0ac01 Update progress.md: document post-sprint SchemaToCpp warning cleanup 2026-02-18 18:15:25 -07:00
Bill
9c0c6bda2f Fix MCPServer warning: remove class-scope json alias from SchemaToCppGenerator 2026-02-18 18:14:56 -07:00
Bill
ed6503b4c8 Sprint 42-45: stabilize modeling tools and implement context, validation, and metrics MCP tooling (Steps 669-688) 2026-02-18 18:11:31 -07:00
Bill
c9e96a5cca Sprint plans 42-45: review 42, write 43-45 
Sprint 42 (reviewed): fixed HiveMind-specific example in smoke test step,
added review notes clarifying asToolResponse usage and test file pattern.

Sprint 43: Cross-File Context Assembly — WorkspaceFileIndex, ContextSliceAssembler,
TokenBudgetEnforcer, whetstone_assemble_context MCP tool (Steps 674-678).

Sprint 44: Taskitem Self-Containment Validator — PrerequisiteOpResolver,
SelfContainmentScorer, TaskitemQualityAuditor, whetstone_validate_taskitem MCP
tool (Steps 679-683). Directly addresses whether taskitem token reduction is real.

Sprint 45: Agent Session Metrics + A/B Harness — AgentSessionRecorder,
TaskCompletionMetrics, ABTestComparison, whetstone_start_recording +
whetstone_get_metrics MCP tools (Steps 684-688). Produces the measured
comparison between Whetstone-assisted and baseline agent runs.

All sprints are generic editor tooling — no coupling to external systems.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-18 17:10:50 -07:00
Bill
17c4cd252a Sprint 41: wire whetstone_schema_to_cpp + whetstone_generate_dispatch_table (Steps 664-668) 
Two C++ generators existed since Steps 634/642 but were never registered as
MCP tools. This sprint is pure plumbing — no new logic, just wiring.

Steps:
  664 - RegisterCodegenTools.h: whetstone_schema_to_cpp handler (12/12)
  665 - RegisterCodegenTools.h: whetstone_generate_dispatch_table handler (12/12)
  666 - MCPServer.h + RegisterOnboardingAndAllTools.h + tools.json wired (8/8)
  667 - whetstone_mcp rebuilt, smoke tested: 84 tools live, both calls return success
  668 - Sprint41IntegrationSummary.h (8/8)

Total: 40/40 passing. tool count 82 → 84.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-18 16:52:29 -07:00
Bill
011221eea1 Sprint 41: plan + taskitems for codegen MCP wiring 
Two C++ generators exist (Steps 634, 642) but aren't registered as MCP tools.
Sprint 41 is pure plumbing — wire them following the RegisterArchitectIntakeTools
pattern from Sprint 36.

- sprint41_plan.md: 5-step plan (Steps 664-668), architecture gates, exact
  tools.json entries to add, test counts and test cases per step
- sprint41_taskitems.json: AnnotatedTaskitem format, fully self-contained,
  with prerequisiteOps pointing to exact files to read before starting each step

Result: whetstone_schema_to_cpp + whetstone_generate_dispatch_table become
live MCP tools callable by Claude Code (tool count 82 → 84).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-18 16:40:04 -07:00
Bill
f13df10c6c Step 663: sprint 40 integration summary 2026-02-17 22:17:37 -07:00
Bill
5151e6085a Step 662: cross-session context bridge model 2026-02-17 22:16:06 -07:00
Bill
8c178644a6 Step 661: pilot queue panel model 2026-02-17 22:15:13 -07:00
Bill
782af1a77f Step 660: inference job generator model 2026-02-17 22:14:21 -07:00
Bill
c5d7b5b0ad Step 659: entropy scanner model 2026-02-17 22:13:24 -07:00
Bill
796d052733 Step 658: phase 40a integration 2026-02-17 22:12:30 -07:00
Bill
33e887fd8b Step 657: energy context status model 2026-02-17 22:11:38 -07:00
Bill
295163e298 Step 656: apiary browser panel model 2026-02-17 22:10:44 -07:00
Bill
e4d9a72a3c Step 655: swarm status panel model 2026-02-17 22:09:48 -07:00
Bill
34455006a1 Step 654: HiveMind job publisher model 2026-02-17 21:57:28 -07:00
Bill
f4259d9864 Step 653: sprint 39 integration summary 2026-02-17 21:56:30 -07:00
Bill
8905076b0d Step 652: local telemetry model 2026-02-17 21:55:20 -07:00
Bill
ea98c95e5d Step 651: plugin manifest model 2026-02-17 21:54:23 -07:00
Bill
96d98fa558 Step 650: HiveMind auto-update model 2026-02-17 21:53:29 -07:00
Bill
30b8b07d5e Step 649: package script generator 2026-02-17 21:52:36 -07:00
Bill
319b6734d0 Step 648: phase 39a integration 2026-02-17 21:51:45 -07:00
Bill
c05e83ec75 Step 647: self-modification safety guard 2026-02-17 21:50:51 -07:00
Bill
90975fde39 Step 646: in-editor test runner model 2026-02-17 21:49:59 -07:00
Bill
bbf6c06d23 Step 645: project AST CMake generator 2026-02-17 21:49:06 -07:00
Bill
97acad04aa Step 644: self-hosting project config 2026-02-17 21:47:58 -07:00
Bill
0ae1ab830a Step 643: sprint 38 integration summary 2026-02-17 21:46:54 -07:00
Bill
9f37be1550 Step 642: job dispatch table generator 2026-02-17 21:45:40 -07:00
Bill
ec74db1275 Step 641: SQLite data layer generator 2026-02-17 21:44:38 -07:00
Bill
3026c29a1e Step 640: MQTT boilerplate generator 2026-02-17 21:43:39 -07:00
Bill
106f5a45bd Step 639: project skeleton generator 2026-02-17 21:42:38 -07:00
Bill
9e30117aa1 Step 638: phase 38a integration 2026-02-17 21:41:34 -07:00
Bill
aa1a52cb55 Step 637: platform CMake target generator 2026-02-17 21:40:36 -07:00
Bill
748a173b0f Step 636: drone error synthesis 2026-02-17 21:39:37 -07:00
Bill
6b067c6800 Step 635: capability declaration generator 2026-02-17 21:38:39 -07:00
Bill
9130277713 Step 634: schema to C++ generator 2026-02-17 21:37:36 -07:00
Bill
98eae97f24 Sprint 37: architecture refactor pass 2026-02-17 21:32:46 -07:00
Bill
b5f03bd7ae Step 633: Sprint 37 integration summary 2026-02-17 21:29:33 -07:00
Bill
9373b604dd Step 632: agent task status overlay 2026-02-17 21:26:57 -07:00
Bill
0a29faaeef Step 631: background task slots 2026-02-17 21:24:03 -07:00
Bill
c78d1d82ac Add step 630 chat session persistence 2026-02-17 21:21:20 -07:00
Bill
695a4bc088 Add step 629 chat context auto-injection 2026-02-17 21:19:00 -07:00
Bill
8c3c08e9b9 Add step 628 phase 37a integration 2026-02-17 21:15:19 -07:00