bill/whetstone_DSL
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
752 Commits 2 Branches 0 Tags
bfe44cd6d8f3dfacb3154d8338d9bcd1fd8d68fc
Commit Graph

42 Commits

Author SHA1 Message Date
Bill
9fe3c1aa93 Add MCP compatibility ledger tool and first-pass Go/Rust codegen hardening 2026-02-25 22:46:33 -07:00
Bill
61e3f6ca32 Complete sprint 141-145 scaffolding, tooling, and tests 2026-02-24 15:34:10 -07:00
Bill
1c0645b2f9 Implement sprints 118-119 distributed failure evidence and triage 2026-02-24 12:31:17 -07:00
Bill
b9e666dc9c Implement sprints 93-117 models, MCP tools, and tests 2026-02-24 12:15:41 -07:00
Bill
aa5a45bb75 Implement sprint 92 interop models, tools, and tests 2026-02-24 11:34:54 -07:00
Bill
33103b5d71 Add migration planning tools and step899-908 test suite 2026-02-22 19:21:19 -07:00
Bill
18c9660baf Sprint 66 (Steps 889-898): Runtime Semantics Packs — framework and platform awareness 
Adds 8 graduation headers: RuntimeSemanticsPack, RuntimePackLoader,
RuntimeAssumptionExtractor, RuntimeAwareLowering, RuntimeRaisingPolicy,
RuntimeVerificationPlugin, RuntimeCompatibilityRiskReport, RuntimeProfileStore.
MCP tools: whetstone_get_runtime_assumptions + whetstone_set_runtime_profile.
All 10 steps pass (86 tests total across sprint 66).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-22 19:09:26 -07:00
Bill
0282e7ebb7 Sprint 65: Parallel Pair Upgrades and Queue Optimization — Steps 879-888 
Implements priority-aware pair-upgrade queue with starvation prevention:
- PairUpgradeQueue: enqueue/dequeue/getActive sorted by priority (step 879)
- UpgradePriorityPolicy: critical/revenue/coverage/experimental classes (step 880)
- ParallelDispatchOptimizer: schedule N pairs with blocked-pair constraints (step 881)
- StarvationPrevention: detect and promote starved pairs (step 882)
- QueueHealthScorer: stall-rate-based health scoring (step 883)
- RetryBackoffStrategy: exponential backoff with max-attempts guard (step 884)
- whetstone_enqueue_pair_upgrade MCP tool (step 885)
- whetstone_get_upgrade_queue MCP tool with priority sorting (step 886)
- UpgradeQueueObservabilityPanel: snapshot model for queue visibility (step 887)
- Sprint65IntegrationSummary (step 888)

All 10 steps passing (94 tests). Routing rule: critical-tier regressions
preempt all experimental upgrades.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-22 18:58:04 -07:00
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
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
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
f03e73dbf3 Add step 617 initialize instructions field 2026-02-17 20:47:58 -07:00
Bill
39dbb220f0 Add step 616 queue readiness MCP tool 2026-02-17 20:46:07 -07:00
Bill
ba620c3051 Add step 615 taskitem generation MCP tool 2026-02-17 20:43:37 -07:00
Bill
8b7537ad86 Add step 614 architect intake MCP tool 2026-02-17 20:41:10 -07:00
Bill
f7c514e705 Refactor large headers and enforce architecture constraints 2026-02-17 08:47:26 -07:00
Bill
842f1afc79 Step 421: add one-call workspace onboarding MCP tool 2026-02-16 16:30:06 -07:00
Bill
6d5a2be423 Step 420: add MCP human review interface 2026-02-16 16:19:52 -07:00
Bill
73e64295f2 Step 387: add orchestrator event stream APIs 2026-02-16 13:01:15 -07:00
Bill
448d051077 Step 382: add orchestrator RPC and MCP tools 2026-02-16 12:47:58 -07:00
Bill
a026743676 Step 330: Review Gates (12/12 tests) 
Configurable auto-approve rules for review gate. Default policy auto-approves
deterministic/template with >=0.9 confidence. @Review(required) always
overrides. Policy serialization, wildcard rules, and 2 new MCP tools.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-15 19:23:06 -07:00
Bill
6352a04836 Step 329: Routing RPC + MCP Tools (12/12 tests) 
4 new RPC methods and MCP tools for routing and worker dispatch:
routeTask, routeAllReady, executeTask, getRoutingExplanation.
Template workers auto-approve getter/setter patterns.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-15 19:20:00 -07:00
Bill
cc352af68e Step 324: Workflow RPC + MCP Tools (12/12 tests) 
8 new RPC methods and MCP tools for workflow lifecycle management:
create, inspect, assign, complete, reject, save. Role-based access
control enforced — Linter read-only, Refactor/Generator can mutate.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-15 17:00:52 -07:00
Bill
0d51a6fe4c Steps 309-319: Sprint 11 Phases 11d-e — Kotlin/C# languages + workflow annotation foundation 
Phase 11d (Steps 309-313): Kotlin + C# parsers and generators
- KotlinParser (regex-based): fun, suspend fun, class, data class, val/var
- KotlinGenerator: idiomatic Kotlin output with type mappings
- CSharpParser (regex-based): methods, async, class, interface
- CSharpGenerator: Allman braces, foreach, Task async, LINQ types
- Pipeline integration for both languages, 10 parsers + 10 generators

Phase 11e (Steps 314-319): Workflow annotation foundation
- AnnotationInference: generalized multi-subject inference engine
- Subject 9 routing annotations: ContextWidth, Review, Ambiguity,
  Automatability, Priority, ImplementationStatus
- SkeletonAST: project specification before code exists
- Architect tooling: createSkeleton, addSkeletonNode, getProjectModel,
  inferAnnotations RPCs + 4 MCP tools (42+ total)
- Inference-to-routing bridge: complexity→ambiguity, getter→deterministic
- TrainingDataExporter + TrainingDataGenerator scaffolding

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-15 15:50:06 -07:00
Bill
d4a3609050 Steps 290-294: Phase 11a — Semanno format, annotation codegen, visitor dispatch (60/60 tests) 
Semanno comment format standard (@semanno:type(key=value)) with emitter/parser
covering all 67+ annotation types. SemannoAnnotationImpl CRTP mixin provides
default visitor implementations for all 56 extended annotation methods across
7 language generators. Virtual inheritance resolves diamond ambiguity between
ProjectionGenerator and SemannoAnnotationImpl.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-13 18:41:31 +00:00
Bill
8cbeef5af4 Steps 284-289: Phase 10e — environment layer, host boundary nodes, MCP env tools (200/200 tests) 
Completes Sprint 10. Adds EnvironmentSpec AST node, capability validation
(E0501), annotation compatibility checks (E0502-E0505), env-aware lowering
hints, 3 host boundary AST nodes (HostCall, ScheduleTask, ModuleLoad),
and 4 MCP environment tools. 38 MCP tools total.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-13 05:56:02 +00:00
Bill
976161dc4a Steps 266-268: Phase 10a — semantic annotation core + sidecar persistence (32/32 tests) 
Step 266: 5 semantic annotation AST types (Intent, Complexity, Risk,
Contract, SemanticTag) with JSON roundtrip and compact AST integration.
Step 267: Sidecar AST persistence (.whetstone/<file>.ast.json) with
save/load/list RPC methods, MCP tools, and permission enforcement.
Step 268: Phase 10a integration tests — multi-file sidecar workflow,
all 5 types in compact view, idempotent roundtrip, source isolation.

Also includes Sprint 10 plan, GUI/installer polish, and Emacs integration fixes.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-12 16:01:56 +00:00
Bill
c36fd92045 Steps 263-265: Phase 9e — save buffer to disk, undo/redo, integration tests 
Step 263: saveBuffer/saveAllBuffers RPC methods write editBuf to disk with
workspace path resolution and parent dir creation. 12/12 tests.

Step 264: State-based undo/redo via HeadlessUndoStack. Snapshots recorded
automatically before mutations; undo/redo restore AST + editBuf. 12/12 tests.

Step 265: Phase 9e integration tests — save after undo/redo, mixed undo
states across buffers, full open→mutate→diagnose→undo→redo→save. 8/8 tests.

Phase 9e complete: 32/32 tests. Sprint 9 total: 244/244 across 5 phases.
34 MCP tools.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-12 01:27:23 +00:00
Bill
eab979bae3 Step 261: project-wide search and refactor (searchProject, renameSymbol) 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-11 20:27:47 +00:00
Bill
8a461df47e Step 260: project-wide diagnostics (getProjectDiagnostics) 
Diagnostics across all open files in one call, grouped by file path.
Includes cross-file E0400 warnings for undefined imports, with optional
severity filter and file glob filter. 12/12 tests pass.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-11 20:13:46 +00:00
Bill
ac5b7e21c8 Step 258: project model and workspace indexing (Phase 9d start) 
Adds multi-buffer management via openFile/closeFile/listBuffers/setActiveBuffer
RPC methods, plus indexWorkspace for scanning workspace files without opening
them. Language auto-detected from extension. 27 MCP tools total (was 22).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-11 19:43:53 +00:00
Bill
850bb8f927 Step 256: batch query endpoint for multi-query round-trips 
batchQuery accepts array of sub-queries, returns all results in one
response. Errors in individual sub-queries don't affect others.
22 MCP tools total. 12/12 tests pass.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-11 16:06:54 +00:00
Bill
fcccaeb866 Step 252: diagnostic delta streaming (getDiagnosticsDelta, version tracking) 
DiagnosticVersionTracker records snapshots and computes added/removed deltas
between versions. Agents can efficiently check if their fix resolved an error
without re-fetching all diagnostics. 21 MCP tools total.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-11 15:45:31 +00:00
Bill
fbc7b6bce2 Step 251: quick-fix actions as RPC mutations (getQuickFixes, applyQuickFix) 
Concrete mutation objects for each diagnostic fix. getQuickFixes returns
reviewable fixes with categories; applyQuickFix applies the fix and reports
whether the diagnostic cleared. Heuristic fixes for missing return and
unused variables. 20 MCP tools total.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-11 15:41:56 +00:00
Bill
14c2fc218a Step 250: structured diagnostic format (error codes, nodeIds, fix suggestions) 
Unified diagnostic stream merging parse errors (E01xx), annotation validation
(E02xx), and strategy violations (E03xx) with severity levels, AST node
references, and machine-applicable fix mutations. New getDiagnostics RPC
method with severity/source filtering. 18 MCP tools total.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-11 15:36:24 +00:00
Bill
fbff0cedd0 Step 248: compact AST response format (subtree, diff, version tracking) 
Adds token-efficient AST queries: compact mode (<30% of full size),
subtree extraction by nodeId, version-tracked AST diff after mutations,
and tokenEstimate on all responses. 12/12 tests pass, 17 tools total.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-11 06:29:17 +00:00
Bill
1131fdf73d Step 247: file operation tools for MCP (read, write, create, diff, list) 
Adds 5 workspace-aware file I/O tools to the MCP server so agents can
manage files without a GUI. All paths are resolved against --workspace
root with escape-rejection security. 12/12 tests pass, tool count now 15.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-11 05:59:02 +00:00
Bill
80b5a199cb Sprint 7 Phase 7b: MCP server with tools, resources, and prompts (Steps 207-213) 
- Step 207: MCPServer.h — MCP protocol core with JSON-RPC 2.0 stdio transport,
  initialize/initialized handshake, capabilities (tools, resources, prompts)
- Step 208: 5 AST tools — whetstone_get_ast, whetstone_mutate, whetstone_batch_mutate,
  whetstone_get_scope, whetstone_get_call_hierarchy
- Step 209: 5 annotation/generation tools — whetstone_suggest_annotations,
  whetstone_apply_annotation, whetstone_generate_code, whetstone_run_pipeline,
  whetstone_project_language
- Step 210: 5 MCP resources — ast, diagnostics, libraries, annotations, settings
- Step 211: 4 MCP prompts — annotate_module, cross_language_projection,
  security_audit, refactor_memory
- Step 212: MCPBridge.h — stdio transport with Content-Length framing,
  bridges MCP to Whetstone JSON-RPC
- Step 213: MCP server tests — 90/90 assertions pass

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-10 07:45:11 -07:00