cc-codeconductor 0.4.2 → 0.4.3

package/README.md

@@ -52,12 +52,41 @@ contracts, task cards, and risk-based routing.
 >   installs the full preset (agents, prompts, skills, commands, settings) for the
 >   chosen runner; use `--locale=es` to inject Spanish-aware instructions into
 >   agent files, or rely on the locale saved during `init`
+> - **Stack-specific presets (v0.4.0)**: `ts-next-drizzle`, `spring-kotlin-jpa`,
+>   `laravel-tall`, `python-data-api` — bundle `architect` + `implementer`
+>   contracts tuned to a single framework so `install preset` drops in the right
+>   defaults for that stack.
+> - **9 specialized skills (v0.4.0)**: `drizzle-schema-architect`,
+>   `tailwind-responsive-auditor`, `seo-analytics-injector`,
+>   `jpa-nplusone-detector`, `spring-auth-auditor`, `livewire-alpine-bridge`,
+>   `fastapi-pydantic-strict`, `tdd-mutation-tester`, `auth-token-inspector` —
+>   loaded automatically by the matching preset.
+> - **Workflow Loop Core (v0.4.0)** — 8-phase pipeline
+>   (`intake → structure → design → test → implement → validate → council →
+>   compact`) with operational guardrails (wall-clock timeout, max files
+>   modified, max lines changed) and human-in-the-loop STOP gates after Design
+>   and Council Verdict.
+> - **Council consensus v0.4.0** — agent confidence thresholds
+>   (`< 0.6` per-agent or `< 0.7` average escalates) and a `complianceVeto`
+>   channel that overrides majority the same way `securityVeto` does.
+> - **Goal orchestration (v0.4.0)** — `goal` planner writes
+>   `.codeconductor/current-goal.yml`; the orchestrator delegates tasks in
+>   dependency order and blocks dependents when a prerequisite is `blocked`.
+> - **Memory compression + escalation emitter (v0.4.0)** — Phase 5 memory index
+>   + token budget hook keeps inter-agent context below the configured budget;
+>   the loop controller emits escalation reports when guardrails fire.
+> - **Parallel subagents (v0.4.0)** — risk-based routing policy v0.4.0 enables
+>   parallel execution for eligible agent sequences (architect + implementer
+>   pattern, council verdict fan-out).
 > - Manual presets for OpenCode, Claude Code, and Codex
 > - Versioned Agent Contracts
 > - Routing Policy documentation
 > - Task Card, Scorecard, and workflow templates
 > - Spring Boot/Kotlin and Python/Django workflow guidance
 >
+> See [docs/v0.4.0-release-notes.md](docs/v0.4.0-release-notes.md) for the
+> full v0.4.0 feature breakdown.
+>
 > What does not exist yet:
 >
 > - Runtime sandbox enforcement
@@ -131,14 +160,19 @@ Task Card → Risk Classification → Routing Policy → Conductor Agent → Del
 - Spring Boot / Kotlin workflow
 - Python / Django workflow guidance
 - 12 core Conductor Agents
-- Routing Policy v0.3.0
+- Routing Policy v0.4.0
 - Task Card template
 - Scorecard template
 - End-to-end example
 - YAML-driven model configuration
 - Provider-agnostic `AgentContract` abstraction with target renderers for Claude, OpenCode, Codex, and Agy
-- Council consensus engine (`councilConsensus()`) for multi-agent governance with majority/unanimous algorithms and security veto
+- Council consensus engine (`councilConsensus()`) for multi-agent governance with majority/unanimous algorithms, security veto, **compliance veto**, and **agent confidence thresholds** (v0.4.0)
 - Phase 5 runtime modules — scoped context injection, TDD history compaction, concise inter-agent messaging, and token budget enforcement in the compile-fix loop
+- **Workflow Loop Core (v0.4.0)** — 8-phase pipeline (`runWorkflowPipeline`) with wall-clock / files-modified / lines-changed guardrails and STOP gates at Design and Council Verdict
+- **Stack-specific presets (v0.4.0)** — `ts-next-drizzle`, `spring-kotlin-jpa`, `laravel-tall`, `python-data-api`
+- **9 specialized skills (v0.4.0)** — drizzle-schema-architect, tailwind-responsive-auditor, seo-analytics-injector, jpa-nplusone-detector, spring-auth-auditor, livewire-alpine-bridge, fastapi-pydantic-strict, tdd-mutation-tester, auth-token-inspector
+- **Goal orchestration (v0.4.0)** — `goal` planner + `goal-state` writer feed the orchestrator's dependency-order delegation loop
+- **Memory compression + escalation emitter (v0.4.0)** — keeps inter-agent context within token budget and surfaces guardrail breaches as escalation reports
 
 ---
 
@@ -226,6 +260,43 @@ Files installed per target:
 
 With `--global`, files are written under `~/` instead of `./`.
 
+#### Stack-specific presets (v0.4.0)
+
+Four stack-specific presets now ship in `presets/` and are registered in
+`src/core/presets/preset-registry.ts`. Each one bundles a tuned
+`architect.md` and `implementer.md` for a single stack, plus the matching
+specialized skills (see below).
+
+| Preset              | Stack                                                      | Contracts included        |
+| ------------------- | ---------------------------------------------------------- | ------------------------- |
+| `ts-next-drizzle`   | Next.js / Astro, Tailwind, Drizzle ORM, Bun, Postgres      | `architect`, `implementer`|
+| `spring-kotlin-jpa` | Spring Boot, Kotlin/Java, Gradle, JPA, Hibernate           | `architect`, `implementer`|
+| `laravel-tall`      | Laravel, Blade, Livewire, Alpine.js                        | `architect`, `implementer`|
+| `python-data-api`   | Python, FastAPI, Django, uv                                | `architect`, `implementer`|
+
+```ts
+// Programmatic access via the registry
+import { listPresets, getPreset } from 'cc-codeconductor/core/presets/preset-registry';
+
+listPresets();
+// [
+//   { name: 'council',            version: '0.1.0', ... },
+//   { name: 'seo-hotel',          version: '0.3.0', ... },
+//   { name: 'ts-next-drizzle',    version: '0.4.0', ... },
+//   { name: 'spring-kotlin-jpa',  version: '0.4.0', ... },
+//   { name: 'laravel-tall',       version: '0.4.0', ... },
+//   { name: 'python-data-api',    version: '0.4.0', ... },
+// ]
+
+const next = getPreset('ts-next-drizzle');
+```
+
+`init` / `detect` identifies the stack from the project and wires the
+matching specialized skills automatically when you run `install preset`.
+The full set of assets for a stack-specific preset is in
+`presets/<preset-name>/agents/` — copy them manually if you need to apply a
+preset by name.
+
 #### `install council` — install council spec
 
 ```bash
@@ -464,7 +535,7 @@ codeconductor/
 | ---------- | ----------------------------------------------------------- |
 | **v0.2.0** | **CLI: init, detect, install, doctor, update — shipped** ✅ |
 | v0.3.0     | Next.js, FastAPI, generic presets, monorepo support         |
-| v0.4.0     | Provider compatibility matrix and target sync workflows     |
+| **v0.4.0** | **Workflow Loop Core, stack-specific presets, 9 specialized skills, confidence thresholds + compliance veto in council consensus, goal orchestration, memory compression — shipped** ✅ |
 | v0.5.0     | Scorecard CLI, task outcome tracking, prompt regression     |
 | v1.0.0     | Stable contracts, stable routing, documented evaluation     |
 

package/dist/index.js

@@ -11126,7 +11126,7 @@ function validateCouncilSpec(data) {
 function validateConfig(data) {
   return CodeConductorConfigSchema.parse(data);
 }
-var CouncilAgentSpecSchema, CouncilSpecSchema, ProjectProfileSchema, CompileCheckConfigSchema, LoopConfigSchema, CodeConductorConfigSchema, RunnerTargetSchema, InstallStrategySchema, ManifestEntrySchema, InstallManifestSchema, ToolProviderNamesSchema, PermissionProviderNamesSchema, ModelConfigSchema, ContractTargetSchema, ContractFormatSchema, AgentContractSchema, CouncilFindingSchema, CouncilVerdictInputSchema, ConsensusConfigSchema, CouncilVerdictSchema, ClaudeAgentFileSchema, OpenCodeAgentFileSchema, SentryStackFrameSchema, SentryWebhookSchema, GoalTaskSchema, GoalGraphSchema;
+var CouncilAgentSpecSchema, CouncilSpecSchema, ProjectProfileSchema, CompileCheckConfigSchema, LoopConfigSchema, CodeConductorConfigSchema, RunnerTargetSchema, InstallStrategySchema, ManifestEntrySchema, InstallManifestSchema, ToolProviderNamesSchema, PermissionProviderNamesSchema, ModelConfigSchema, ContractTargetSchema, ContractFormatSchema, AgentContractSchema, CouncilFindingSchema, CouncilVerdictInputSchema, ConsensusConfigSchema, CouncilVerdictSchema, ClaudeAgentFileSchema, OpenCodeAgentFileSchema, SentryStackFrameSchema, SentryWebhookSchema, MemoryPointerSchema, MemoryIndexSchema, GoalTaskSchema, GoalGraphSchema;
 var init_schemas = __esm(() => {
   init_zod();
   CouncilAgentSpecSchema = exports_external.object({
@@ -11313,6 +11313,18 @@ var init_schemas = __esm(() => {
     environment: exports_external.string().optional(),
     release: exports_external.string().optional()
   });
+  MemoryPointerSchema = exports_external.object({
+    topic_key: exports_external.string().min(1).max(128),
+    id: exports_external.number().int().positive(),
+    file: exports_external.string().min(1),
+    summary: exports_external.string().min(1).max(200),
+    timestamp: exports_external.string().datetime(),
+    tags: exports_external.array(exports_external.string().max(64)).max(10).optional().default([])
+  });
+  MemoryIndexSchema = exports_external.object({
+    version: exports_external.literal(1),
+    pointers: exports_external.array(MemoryPointerSchema)
+  });
   GoalTaskSchema = exports_external.object({
     id: exports_external.string(),
     title: exports_external.string(),
@@ -12154,7 +12166,7 @@ init_errors();
 // package.json
 var package_default = {
   name: "cc-codeconductor",
-  version: "0.4.2",
+  version: "0.4.3",
   description: "A multi-agent orchestration framework for AI-assisted software engineering workflows.",
   keywords: [
     "ai",
@@ -13920,7 +13932,7 @@ async function writeConfig(projectRoot, config = {}, force = false) {
 init_package_paths();
 
 // src/core/presets/preset-resolver.ts
-var CURRENT_PRESET_VERSION = "v0.3.0";
+var CURRENT_PRESET_VERSION = "v0.4.0";
 function resolvePreset(target, profile) {
   const stack = resolveStack(profile);
   const isMonorepo = profile.signals.some((s) => [
@@ -13983,17 +13995,17 @@ function resolveStack(profile) {
 function resolveAssets(target) {
   switch (target) {
     case "opencode":
-      return ["opencode.jsonc", "agents", "commands", "prompts/v0.3.0", "skills"];
+      return ["opencode.jsonc", "agents", "commands", "prompts/v0.4.0", "skills"];
     case "claude":
-      return ["CLAUDE.md", "settings.json", "commands", "skills", "agents", "prompts/v0.3.0"];
+      return ["CLAUDE.md", "settings.json", "commands", "skills", "agents", "prompts/v0.4.0"];
     case "codex":
-      return ["AGENTS.md", "skills", "prompts/v0.3.0"];
+      return ["AGENTS.md", "skills", "prompts/v0.4.0"];
     case "gemini":
-      return ["agents", "prompts/v0.3.0"];
+      return ["agents", "prompts/v0.4.0"];
     case "cursor":
-      return ["agents", "prompts/v0.3.0"];
+      return ["agents", "prompts/v0.4.0"];
     case "agy":
-      return ["AGENTS.md", "rules", "workflows", "skills", "prompts/v0.3.0"];
+      return ["AGENTS.md", "rules", "workflows", "skills", "prompts/v0.4.0"];
   }
 }
 
@@ -15708,6 +15720,14 @@ function renderHuman(inventory, defaultTarget) {
       lines.push(`  - ${wf}`);
     }
   }
+  lines.push("");
+  lines.push("Stack-specific presets (v0.4.0):");
+  lines.push("  ts-next-drizzle     Next.js / Astro, Tailwind, Drizzle ORM, Bun, Postgres");
+  lines.push("  spring-kotlin-jpa   Spring Boot, Kotlin/Java, Gradle, JPA, Hibernate");
+  lines.push("  laravel-tall        Laravel, Blade, Livewire, Alpine.js");
+  lines.push("  python-data-api     Python, FastAPI, Django, uv");
+  lines.push("  Browse: presets/<preset-name>/agents/ — copy into the target runner.");
+  lines.push("  Registry: src/core/presets/preset-registry.ts (listPresets / getPreset).");
   return lines.join(`
 `);
 }
@@ -17537,27 +17557,47 @@ Usage: npx cc-codeconductor <command> [options]
 
 Commands:
   init                    Initialize CodeConductor in a project
-  detect                 Detect project stack and recommended presets
-  install council        Install generated council spec files to runner targets
-  install preset         Install full preset (agents, prompts, skills, commands)
-  install lsp            Install and configure LSP servers for AI coding tools
-  seo audit              Run SEO audit on a URL or sitemap
-  seo llms               Generate llms.txt from a URL or sitemap
-  doctor                 Validate configuration and generated files
-  update                 Update installed presets
-  help / cc-help         Show preset inventory (skills, subagents, commands)
-  debt-harvest / harvest Scan source files for deferred debt items
-  goal / cc-goal        Plan goal into task graph with dependencies
+  detect                  Detect project stack and recommended presets
+  install council         Install generated council spec files to runner targets
+  install preset          Install full preset (agents, prompts, skills, commands)
+  install lsp             Install and configure LSP servers for AI coding tools
+  seo audit               Run SEO audit on a URL or sitemap
+  seo llms                Generate llms.txt from a URL or sitemap
+  doctor                  Validate configuration and generated files
+  update                  Update installed presets
+  help / cc-help          Show preset inventory (skills, subagents, commands)
+  debt-harvest / harvest  Scan source files for deferred debt items
+  goal / cc-goal          Plan goal into task graph with dependencies
 
 Options:
-  --help, -h             Show this help message
-  --version, -v          Show package version
-  --dry-run              Show what would happen without writing files
-  --force                Allow overwriting existing files
-  --global               Install to home directory (~/.claude, ~/.opencode, etc.)
-  --output, -o           Output mode: human or json
-  --lang                 Comma-separated list of languages (e.g., typescript,php,python)
-  --locale               Instruction language for agent files: en (default) | es
+  --help, -h              Show this help message
+  --version, -v           Show package version
+  --dry-run               Show what would happen without writing files
+  --force                 Allow overwriting existing files
+  --global                Install to home directory (~/.claude, ~/.opencode, etc.)
+  --output, -o            Output mode: human or json
+  --lang                  Comma-separated list of languages (e.g., typescript,php,python)
+  --locale                Instruction language for agent files: en (default) | es
+  --target                Runner target: opencode, claude, codex, gemini, cursor, agy, all
+
+Stack-specific presets (v0.4.0, registered in preset-registry):
+  ts-next-drizzle         Next.js / Astro, Tailwind, Drizzle ORM, Bun, Postgres
+  spring-kotlin-jpa       Spring Boot, Kotlin/Java, Gradle, JPA, Hibernate
+  laravel-tall            Laravel, Blade, Livewire, Alpine.js
+  python-data-api         Python, FastAPI, Django, uv
+  Listed programmatically via listPresets() in src/core/presets/preset-registry.ts.
+  Stack detection wires matching specialized skills automatically when
+  init/detect identifies the stack.
+
+Workflow Loop Core (v0.4.0):
+  runWorkflowPipeline() in src/core/pipeline/workflow-loop.ts runs the
+  8-phase loop (intake -> structure -> design -> test -> implement ->
+  validate -> council -> compact) with wall-clock, files-modified and
+  lines-changed guardrails and STOP gates after Design and Council.
+
+Council consensus v0.4.0:
+  Per-agent confidence thresholds (< 0.6 or average < 0.7 escalate)
+  and a complianceVeto channel that overrides majority like securityVeto.
 
 Examples:
   npx cc-codeconductor init
@@ -17586,6 +17626,16 @@ Examples:
   npx cc-codeconductor seo audit --sitemap https://example.com/sitemap.xml --format markdown
   npx cc-codeconductor seo llms --sitemap https://example.com/sitemap.xml
   npx cc-codeconductor seo llms --url https://example.com --output llms.txt
+  npx cc-codeconductor goal "Add user authentication"
+  npx cc-codeconductor cc-goal "Implement CRUD for invoices"
+  npx cc-codeconductor help --target opencode
+  npx cc-codeconductor help --target claude --output json
+
+Docs: https://github.com/lgzarturo/codeconductor/tree/main/docs
+  docs/v0.4.0-release-notes.md   v0.4.0 feature breakdown
+  docs/routing-policy.md         Risk-based routing (v0.4.0)
+  docs/prompt-versioning.md      Agent contract versions
+  docs/usage-cli.md              Detailed CLI reference
 `;
 }
 async function routeCommand(args, projectRoot) {
@@ -17744,6 +17794,8 @@ async function runCli(args) {
         const data = result.data;
         if ("help" in data) {
           console.log(data.help);
+        } else if ("message" in data && typeof data.message === "string") {
+          console.log(data.message);
         } else {
           if ("errors" in data && Array.isArray(data.errors) && data.errors.length > 0) {
             data.errors.forEach((e) => console.error(e));

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cc-codeconductor",
-  "version": "0.4.2",
+  "version": "0.4.3",
   "description": "A multi-agent orchestration framework for AI-assisted software engineering workflows.",
   "keywords": [
     "ai",

package/presets/agy/workflows/cc-pipeline.md

@@ -0,0 +1,69 @@
+---
+name: cc-pipeline
+description: Run the full 8-phase multi-agent workflow loop (Intake, Structure, Design, Test, Implement, Validate, Council, Compact).
+---
+
+# Multi-Agent Workflow Pipeline Loop
+
+Scope: $ARGUMENTS
+
+This workflow orchestrates the complete 8-phase development loop, combining Ponytail minimalism, DDD→SDD→TDD pipeline, and autonomous governance.
+
+---
+
+## Phase 1 — Intake (task-coach)
+
+The `task-coach` agent collects the raw request, refines it with the user, and validates that all fields of the Task Card are filled out (title, type, risk, scope, context, acceptance criteria, constraints).
+
+---
+
+## Phase 2 — Structure (prompt-structurer)
+
+Prunes the Task Card of redundant context, wraps parameters in XML tags (`<context>`, `<constraints>`, `<task>`, `<scope>`), and retrieves lightweight AST signatures instead of complete files to minimize token footprints.
+
+---
+
+## Phase 3 — Design (architect)
+
+The `architect` reads AST signatures, creates the Technical Plan, and defines the Edge Case Matrix detailing potential failure modes and boundary conditions.
+
+> [!IMPORTANT]
+> **STOP GATE (SDD SPECIFICATION GATE):** Pauses execution and requests manual operator approval before writing any code or tests.
+
+---
+
+## Phase 4 — Test (adversarial-tester)
+
+The `adversarial-tester` writes the TDD RED tests verifying happy paths, edge cases, and parameters. The test suite must be run to confirm it fails for the correct reasons.
+
+---
+
+## Phase 5 — Implement (implementer)
+
+The `implementer` writes the minimal code to satisfy the tests. The implementer must edit only files within the approved plan scope. If tests fail, run implement-test loop iterations (max 3) before escalating.
+
+---
+
+## Phase 6 — Validate (tester)
+
+Runs validation checks:
+1. **Mutation Testing:** Automatically mutates operators and bounds to verify test assertions are strict (minimum score: 80%).
+2. **Diff Scope Audit:** Scans modified files to prevent out-of-scope code additions or speculative implementations.
+
+---
+
+## Phase 7 — Council Verdict (council)
+
+Reviewer agents audit the diff on 6 axes: Architecture, Security, Product, Delivery, Compliance, and Devil.
+
+- **Veto check:** Security and Compliance reviewers can apply overriding vetoes (`securityVeto` / `complianceVeto`) to block a change.
+- **Confidence check:** Escalates to human operator if individual confidence < 0.6 or average confidence < 0.7.
+
+> [!IMPORTANT]
+> **STOP GATE (VERDICT/MERGE GATE):** Pauses execution after Council consensus to request final manual confirmation before compaction and delivery.
+
+---
+
+## Phase 8 — Compact (compaction-hook)
+
+Prunes RED/GREEN iteration files and writes a persistent summary pointer to `.codeconductor/memory.md` to update the repository memory without exceeding the 40KB file boundary.

package/presets/laravel-tall/agents/architect.md

@@ -0,0 +1,8 @@
+# Agent Contract: Laravel/Livewire Architect (v1.2.0)
+
+## Misión
+Eres el agente arquitecto especializado en el stack TALL. Diseñas las soluciones y los DTOs, e invocas la skill `livewire-alpine-bridge` para estructurar la separación limpia entre PHP y JS.
+
+## Reglas
+1. **Estricto**: Diseña los componentes de Blade pensando en reutilización y modularidad.
+2. **Estricto**: No inventes dependencias externas; prefiere la librería estándar o las oficiales de Laravel (como Jetstream, Livewire).

package/presets/laravel-tall/agents/implementer.md

@@ -0,0 +1,12 @@
+# Agent Contract: Laravel/Livewire Implementer (v1.2.0)
+
+## Misión
+Eres el agente implementador especializado en el stack TALL. 
+Tu única tarea es escribir el código que satisfaga el diseño (SDD) proveído por el Architect.
+No debes proponer nuevas arquitecturas ni instalar dependencias sin escalar la petición.
+
+## Reglas y Restricciones (Hard Constraints)
+1.  **Estricto:** Todo el estado reactivo del frontend DEBE manejarse mediante Alpine.js. Solo usa Livewire para mutaciones que requieran interacción con el backend o la base de datos de Postgres.
+2.  **Estricto:** Las vistas de Blade deben usar el sistema de componentes anónimos y utilidades estandarizadas de Tailwind. Invocación obligatoria de la skill `tailwind-responsive-auditor` antes de terminar.
+3.  **Boundary:** NO modifiques los archivos `.env` o la configuración de `Auth0` bajo ninguna circunstancia. Si necesitas variables de entorno, repórtalo en el Scorecard de salida.
+4.  **TDD Obligatorio:** Si la Task Card tiene el tipo `feature`, debes asegurarte de compilar tu código junto a la suite de tests Pest de PHP.

package/presets/laravel-tall/laravel-tall.yml

@@ -0,0 +1,38 @@
+name: laravel-tall
+version: 0.4.0
+description: Laravel TALL stack preset (Laravel, Blade, Livewire, Alpine.js)
+outputContract: v1
+
+agents:
+  - id: architect
+    role: Laravel/Livewire Architect
+    context: repo-readonly
+    modelHint: strong-reasoning
+    focus:
+      - laravel-tall
+      - livewire-alpine-bridge
+
+  - id: implementer
+    role: Laravel/Livewire Implementer
+    context: repo-write
+    modelHint: practical-coding
+    focus:
+      - laravel-tall
+      - livewire-alpine-bridge
+      - tailwind-responsive-auditor
+
+  - id: tester
+    role: Laravel Tester
+    context: repo-write
+    modelHint: practical-coding
+    focus:
+      - laravel-tall
+      - tdd-mutation-tester
+
+  - id: reviewer
+    role: Laravel Reviewer
+    context: repo-readonly
+    modelHint: analytical
+    focus:
+      - tailwind-responsive-auditor
+      - auth-token-inspector