agentic-orchestrator 0.1.3 → 0.1.4

package/.claude/settings.local.json

@@ -0,0 +1,15 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(cat:*)",
+      "Bash(gh api:*)",
+      "WebFetch(domain:api.github.com)",
+      "WebFetch(domain:raw.githubusercontent.com)",
+      "Bash(npm run:*)",
+      "Bash(npx vitest:*)",
+      "Bash(grep:*)",
+      "Bash(ls:*)",
+      "Bash(wc:*)"
+    ]
+  }
+}

package/CLAUDE.md

@@ -0,0 +1,126 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Build & Development Commands
+
+```bash
+npm run build              # Lint + TypeScript compile
+npm run typecheck          # tsc --noEmit (type-check only)
+npm run lint               # ESLint with --max-warnings 0
+npm run lint:fix           # ESLint with auto-fix
+npm run test               # Vitest with coverage (via Nx)
+npm run run                # Run CLI: tsx apps/control-plane/src/cli/aop.ts
+
+# Run a single test file
+npx vitest run apps/control-plane/test/<file>.spec.ts
+
+# Run tests matching a pattern
+npx vitest run -t "pattern"
+
+# Validation scripts (also run in CI)
+npm run validate:mcp-contracts
+npm run validate:architecture
+npm run validate:docker-mcp
+```
+
+## Architecture
+
+This is an MCP-first, multi-agent orchestrator control plane. The codebase lives in an Nx monorepo with a single application at `apps/control-plane/`.
+
+### Layer Overview
+
+**CLI** (`apps/control-plane/src/cli/`) → **Supervisor** (`supervisor/`) → **Kernel** (`core/kernel.ts`) → **Services** (`application/services/`)
+
+- **CLI**: Entry point at `cli/aop.ts` → delegates to `interfaces/cli/bootstrap.ts`. Commands: `run`, `status`, `resume`, `stop`, `delete`, `cleanup`, `init`, `dashboard`, `retry`, `send`, `attach`, `help`. All responses are structured JSON with `{ ok, data/error }`. Run `aop --help` or `aop help <command>` for usage details.
+- **Kernel** (`core/kernel.ts`, ~900 lines): Deterministic orchestration engine. Manages schema validation, state, locks, plans, patches, gates, merges, and reporting. Delegates to 12+ domain services via port interfaces.
+- **Supervisor** (`supervisor/runtime.ts`): Multi-agent runtime. Resolves providers (codex, claude, gemini, etc.), loads role-specific prompts, orchestrates planning/build/QA waves, manages lease heartbeats.
+- **MCP Tool Runtime** (`mcp/tool-runtime.ts`): Tool execution pipeline with registry-based dispatch, input/output schema validation, role-based authorization, and idempotency tracking via `operation_id`.
+- **Application Services** (`application/services/`): 12+ focused services (plan, patch, gates, QA, locks, merge, deletion, etc.) implementing port interfaces consumed by the kernel.
+
+### Configuration Layer (`agentic/orchestrator/`)
+
+- `policy.yaml` — Commit/patch/merge policies, lock TTL, RBAC, supervisor iteration limits
+- `gates.yaml` — Gate profiles (fast/full/merge) with commands and coverage thresholds
+- `agents.yaml` — Agent roles (planner/builder/qa), provider defaults, prompt paths
+- `prompts/` — Role-specific system prompts
+- `tools/` — MCP tool contracts: `catalog.json` (33 tools), per-tool `schemas/input/` and `schemas/output/`
+- `schemas/` — JSON schemas for policy, state, plan, index, gates, agents, qa_test_index
+
+### Runtime Artifacts (`.aop/`)
+
+- `.aop/features/index.json` — Global feature index (active/blocked/merged features, locks, sessions)
+- `.aop/features/<id>/state.md` — Per-feature state (YAML frontmatter + markdown)
+- `.aop/features/<id>/plan.json` — Versioned plan with optimistic concurrency
+- `.aop/features/<id>/evidence/` — Gate evidence artifacts
+
+## Key Patterns
+
+- **Port-based DI**: Services define interface ports; the kernel implements them. This decouples domain logic from infrastructure.
+- **Schema-driven validation**: All configs and artifacts validated via AJV against JSON schemas. Validation failures return structured errors with retry hints.
+- **Atomic state management**: File locks, version guards, and optimistic concurrency for all state mutations.
+- **Structured error codes**: 45+ error codes with `{ code, message, details: { retryable, requires_human, suggestions } }`.
+- **Tool registry dispatch**: `catalog.json` metadata drives tool routing, replacing switch-based dispatch. Mutating tools require `operation_id` for idempotency.
+
+## Lint Rules to Know
+
+- `no-explicit-any` is **enforced** in source, relaxed in tests
+- `no-floating-promises` and `no-misused-promises` are errors
+- `require-await` is enforced in source, relaxed in tests
+- `consistent-type-imports` is required (use `import type` for type-only imports)
+- `no-console` is an error in source (except `warn`/`error`); allowed in scripts and CLI entry point
+- Unused variables must be prefixed with `_`
+- Zero warnings allowed (`--max-warnings 0`)
+
+## Adding a New CLI Command or Flag
+
+When adding a new command or flag to the CLI, update **all** of the following in the same change:
+
+1. **`apps/control-plane/src/cli/types.ts`** — add the command to the `CliCommand` enum.
+2. **`apps/control-plane/src/cli/cli-argument-parser.ts`** — parse the new flag/command token.
+3. **`apps/control-plane/src/interfaces/cli/bootstrap.ts`** — dispatch the new command.
+4. **`apps/control-plane/src/cli/help-command-handler.ts`** — add or update the entry in `COMMAND_HELP` (both the command summary and its flags list). This is the source of truth for `aop --help` output.
+5. **`CLAUDE.md`** — update the command list in the CLI bullet point above.
+
+## Coverage Thresholds
+
+Lines: 90% | Branches: 90% | Functions: 90% | Statements: 90%
+
+## Updating progress.md
+
+`spec-files/progress.md` is the versioned work log for this repository. **After completing any meaningful code change** (new feature, bug fix, refactor, test coverage improvement, validator change, etc.), append a new numbered entry to the **Completed Tasks** section of `progress.md`.
+
+### Entry format
+
+Each entry must include:
+- A sequential number (increment from the last entry)
+- A short title describing what was done
+- **Goal** — one sentence on why the change was made
+- **Changes made** — bullet list of files modified and what changed; be specific (function names, test counts, metric deltas)
+- **Result** — outcome verification (e.g. `npm test ✅`, `npm run lint ✅`, validator output)
+
+```
+✅ **Entry N — Short Title**
+   - **Goal:** One-sentence description of the problem or objective.
+   - **Changes made:**
+     - `path/to/file.ts` — description of what changed and why.
+     - `apps/control-plane/test/foo.spec.ts` — X tests added covering Y branches.
+   - **Result:** `npm test` ✅ (N test files / M tests passing). `npm run lint` ✅.
+```
+
+### Rules
+
+- **One entry per logical unit of work.** Don't bundle unrelated changes into one entry.
+- **Do not edit or renumber past entries.** The log is append-only.
+- Entries go in the **Completed Tasks** section (before the `## Next Tasks:` heading).
+- The `## Next Tasks:` section lists only work that has **not yet been done**. Move items out of it once completed.
+- After completing work from a spec file, update the **Spec Gap Tracker** table (if present) to mark the item `✅ Complete`.
+
+## Executing a Spec
+
+When beginning work from a spec file (e.g. `spec-files/agentic_orchestrator_*.md`):
+
+1. **Before writing any code**, read the spec and add all planned tasks to the `## Next Tasks:` section of `progress.md`. Use the spec's section numbers as identifiers (e.g. `§3.1 — Add mutating cross-check`).
+2. **As each task completes**, move it out of `## Next Tasks:` and into a new numbered `✅ **Entry N — ...`** in the Completed Tasks section.
+3. **Never leave a completed task in `## Next Tasks:`**. The section must only contain work that hasn't started or isn't finished.
+4. If a task is blocked or deferred, leave it in `## Next Tasks:` with a `[BLOCKED]` or `[DEFERRED]` annotation and a one-line reason.

package/README.md

@@ -10,7 +10,7 @@ It combines:
 
 - a **deterministic kernel** (state, locks, collisions, gates, evidence)
 - a **supervisor runtime** (orchestrator/planner/builder/qa session coordination)
-- a **CLI contract** (`aop <run|status|resume|stop|delete>`) with deterministic spec ingestion, runtime control, and cleanup
+- a **CLI contract** (`aop <run|status|resume|stop|delete|cleanup|init|dashboard|retry|send|attach>`) with deterministic spec ingestion, runtime control, monitoring, and cleanup
 
 > For complete normative requirements, see [agentic_orchestrator_spec.md](spec-files/agentic_orchestrator_spec.md).
 > For implementation continuity and the latest status, see [progress.md](spec-files/progress.md).
@@ -95,6 +95,7 @@ Agentic-Orchestrator/
 ├── .aop/
 │   ├── features/                      # runtime-generated feature artifacts
 │   │   └── index.json                # global orchestration index
+│   ├── analytics/                     # agent performance analytics
 │   └── runtime/
 │       └── operation-ledger/
 ├── agentic/
@@ -102,23 +103,30 @@ Agentic-Orchestrator/
 │   │   ├── policy.yaml
 │   │   ├── gates.yaml
 │   │   ├── agents.yaml
+│   │   ├── multi-project.yaml         # optional multi-project configuration
 │   │   ├── schemas/
 │   │   └── tools.md
 ├── apps/
 │   └── control-plane/
 │       ├── src/
-│       │   ├── cli/                   # aop CLI
+│       │   ├── cli/                   # aop CLI commands and handlers
 │       │   ├── core/                  # deterministic kernel
+│       │   ├── application/
+│       │   │   └── services/          # domain services (cost, reactions, pr-monitor, etc.)
 │       │   ├── providers/             # provider resolution + adapter
 │       │   └── supervisor/            # runtime orchestration loop
-│       ├── test/                      # Vitest suites
+│       ├── test/                      # Vitest suites (68 files / 899 tests)
 │       ├── project.json               # Nx targets
 │       └── vitest.config.ts
+├── packages/
+│   └── web-dashboard/                 # Next.js 14 web dashboard (aop dashboard)
+├── docker/
+│   ├── mcp.Dockerfile
+│   ├── mcp.entrypoint.sh
+│   └── mcp.compose.yaml
 ├── spec-files/
 │   ├── agentic_orchestrator_spec.md
-│   ├── agentic_orchestrator_mcp_formalization_spec.md
-│   ├── agentic_orchestrator_single_global_orchestrator_spec.md
-│   ├── agentic_orchestrator_oop_refactor_spec.md
+│   ├── agentic_orchestrator_feature_gaps_closure_spec.md
 │   └── progress.md                     # implementation continuity log
 └── README.md
 ```
@@ -194,10 +202,10 @@ node dist/apps/control-plane/cli/aop.js run -fi ./.aop/features/my_feature/spec.
 Primary command:
 
 ```bash
-aop <run|status|resume|stop|delete> [options]
+aop <command> [flags]
 ```
 
-If no command is provided, the CLI defaults to `run`.
+If no command is provided, the CLI defaults to `run`. Run `aop help` for the full command list, or `aop help <command>` for per-command flags.
 
 All commands print JSON to stdout. Errors use:
 
@@ -205,6 +213,8 @@ All commands print JSON to stdout. Errors use:
 { "ok": false, "error": { "code": "...", "message": "...", "details": { ... } } }
 ```
 
+Available commands: `run`, `status`, `resume`, `stop`, `delete`, `cleanup`, `init`, `dashboard`, `retry`, `send`, `attach`, `help`.
+
 ### `run`
 
 Starts orchestration for feature specs and returns runtime metadata (`runtime_status`, `queue_depth`, dashboard snapshot, and active feature list).
@@ -347,25 +357,122 @@ Behavior:
 - preview reports planned cleanup for feature files, index/session references, locks, blocked queue entries, worktree, and branch
 - execution removes feature residue from index/runtime state, deletes `.aop/features/<feature_id>`, optionally removes worktree, and optionally removes local branch
 
+### `cleanup`
+
+Removes merged or stale feature artifacts, worktrees, and index residue. Default behavior is preview-only; destructive execution requires `--yes`.
+
+```bash
+# Preview what would be cleaned
+aop cleanup
+
+# Apply cleanup for all eligible (merged/stale) features
+aop cleanup --yes
+```
+
+When `cleanup.auto_after_merge` is enabled in `policy.yaml`, the runtime automatically triggers cleanup after a successful merge.
+
+### `init`
+
+Initialises agentic orchestrator configuration in the current directory. Generates `policy.yaml`, `gates.yaml`, `agents.yaml`, and system prompt templates.
+
+```bash
+# Interactive wizard
+aop init
+
+# Non-interactive (all defaults)
+aop init --auto
+
+# Overwrite existing configuration
+aop init --force
+```
+
+### `dashboard`
+
+Starts the web dashboard server (`packages/web-dashboard/`). Provides a real-time Kanban view of all features, review approval/denial, checkout, and SSE-based live updates.
+
+```bash
+# Start in production mode (default port 3000)
+aop dashboard
+
+# Custom port
+aop dashboard --port 8080
+
+# Development mode (Next.js hot reload)
+aop dashboard --dev
+```
+
+### `retry`
+
+Retries a failed gate or step for a feature. Use `--force` to reset state and force a gate re-run.
+
+```bash
+aop retry --feature-id my_feature
+
+# Force retry regardless of current state
+aop retry --feature-id my_feature --force
+```
+
+### `send`
+
+Sends a message to the active agent session for a feature.
+
+```bash
+aop send --feature-id my_feature --message "focus on the error handling path"
+
+# Positional form
+aop send my_feature "focus on the error handling path"
+```
+
+### `attach`
+
+Attaches interactively to the running agent session for a feature (provider support required).
+
+```bash
+aop attach --feature-id my_feature
+
+# Positional form
+aop attach my_feature
+```
+
+### `help`
+
+Prints the full command list or detailed help for a specific command.
+
+```bash
+aop help
+aop help run
+aop help dashboard
+```
+
 ### CLI Options
 
 Supported options:
 
 | Option                                                | Description                                                                       |
 |-------------------------------------------------------|-----------------------------------------------------------------------------------|
-| `-fi <path>`                                          | Run exactly one spec file                                                         |
-| `-fl <path>`                                          | Resolve all `**/*.md` files recursively in a folder (deterministic lexical order) |
-| `--agent-provider <codex\\|claude\\|gemini\\|custom\\|kiro-cli\\|copilot>` | Provider selection                                                 |
+| `-fi <PATH>`                                          | Run exactly one spec file                                                         |
+| `-fl <PATH>`                                          | Resolve all `**/*.md` files recursively in a folder (deterministic lexical order) |
+| `--batch`                                             | Batch-ingest all specs; skip already-active features (`run`)                      |
+| `--agent-provider <codex\\|claude\\|gemini\\|custom\\|kiro-cli\\|copilot>` | Provider selection                                      |
 | `--agent-model <model-id>`                            | Model selection                                                                   |
 | `--agent-config <json-object>`                        | Additional provider-specific agent config (for example command/args payload)      |
 | `--provider-config-env <ENV_VAR>`                     | Provider auth/config environment variable name                                    |
 | `--transport <mcp\\|inprocess>`                       | Tool transport selection (default `mcp`)                                          |
 | `--takeover-stale-run`                                | Allow stale run-lease takeover during `run`                                       |
-| `--feature-id <id>`                                   | Target feature for `delete`                                                       |
-| `--dry-run [true\\|false]`                            | Delete mode selector (defaults to preview behavior)                               |
-| `--yes`                                               | Confirm destructive `delete` execution                                            |
-| `--remove-worktree [true\\|false]`                    | Whether `delete` removes `.worktrees/<feature_id>` (default `true`)               |
-| `--remove-branch <none\\|safe\\|force>`               | Optional local branch cleanup mode for `delete` (default `none`)                  |
+| `--project <name>`                                    | Select project from `multi-project.yaml` (run, status, resume, retry)            |
+| `--feature-id <id>`                                   | Target feature for `delete`, `cleanup`, `retry`, `send`, `attach`                |
+| `--dry-run [true\\|false]`                            | Preview-only mode for `delete` and `cleanup`                                      |
+| `--yes`                                               | Confirm destructive `delete` or `cleanup` execution                               |
+| `--remove-worktree [true\\|false]`                    | Whether to remove `.worktrees/<feature_id>` (default `true`)                      |
+| `--remove-branch <none\\|safe\\|force>`               | Local branch cleanup mode (default `none`)                                        |
+| `--summary`                                           | Condensed one-line-per-feature output (`status`)                                  |
+| `--all`                                               | Aggregate across all projects (`status`); delete all features (`delete`)          |
+| `--auto`                                              | Non-interactive init with all defaults (`init`)                                   |
+| `--force`                                             | Overwrite existing config (`init`); force retry regardless of state (`retry`)     |
+| `--port <number>`                                     | Dashboard listen port (default `3000`)                                            |
+| `--dev`                                               | Start dashboard in Next.js dev mode                                               |
+| `--foreground`                                        | Keep dashboard server in the foreground                                           |
+| `--message <text>`                                    | Message to deliver to agent session (`send`)                                      |
 
 Validation behavior:
 
@@ -414,15 +521,21 @@ Current defaults include:
 - implementation constraints: `workspace=nx`, `framework=vitest`
 - merge requires explicit user approval token
 - supervisor iteration loop is policy-configurable via `supervisor.max_iterations_per_phase` (default `6`)
+- `budget.per_feature_limit_usd` (default `50.00`) and `budget.alert_threshold` (default `0.8`) for cost enforcement
+- `reactions` config: per-event retry rules (`gate_failed`, `agent_stuck`, `collision_detected`, `ready_to_merge`, `changes_requested`)
+- `issue_tracker` config: provider (`github`/`linear`/`jira`), credentials, and field mapping
+- `cleanup.auto_after_merge` / `cleanup.grace_period_seconds`: automatic merged-artifact removal
 
 ### Gates (`agentic/orchestrator/gates.yaml`)
 
 Default profile modes:
 
-- `fast`
+- `fast` — supports `{base_branch}` / `{feature_id}` interpolation for incremental runs
 - `full`
 - `merge`
 
+Gate steps support `parallel_group` and `depends_on` fields for parallel execution waves. Steps within the same `parallel_group` run concurrently via `Promise.allSettled()`.
+
 Coverage parser:
 
 - `lcov` from `coverage/control-plane/lcov.info`
@@ -432,8 +545,17 @@ Coverage parser:
 - role-specific system prompt paths
 - default provider/model/config-env fallback values
 - optional `runtime.provider_configs.<provider>` objects for provider-specific payloads (for example `kiro-cli chat --agent dev`)
+- `worktree.post_create` commands and `worktree.symlinks` for workspace hook automation
 - stack-specific examples: [`example-configurations/node/`](example-configurations/node) and [`example-configurations/java/`](example-configurations/java)
 
+### Multi-Project (`agentic/orchestrator/multi-project.yaml`)
+
+Optional. Defines multiple independent projects in one repository. Pass `--project <name>` on the CLI to scope commands to a project. `aop status --all` aggregates across all projects. Each project can override `policy` and `gates` paths.
+
+### Adapter Registry (`agentic/orchestrator/adapters.yaml`)
+
+Optional. Registers custom adapters for `notification-channel`, `activity-detector`, and `scm-provider` slots. Resolves at kernel/supervisor boot.
+
 ### Example configuration bundles
 
 - overview: [`example-configurations/README.md`](example-configurations/README.md)
@@ -541,7 +663,7 @@ All failures return structured error payloads with stable error codes.
 
 ### MCP contract artifacts
 
-- `agentic/orchestrator/tools/catalog.json`: canonical tool list, roles, handler bindings, mutating/idempotency requirements, and schema refs.
+- `agentic/orchestrator/tools/catalog.json`: canonical tool list (33 tools), roles, handler bindings, mutating/idempotency requirements, and schema refs.
 - `agentic/orchestrator/tools/protocol.json`: pinned MCP protocol + SDK metadata and required transports.
 - `agentic/orchestrator/tools/errors.schema.json`: normalized error envelope contract.
 - `agentic/orchestrator/tools/schemas/input/*.schema.json`: per-tool request schemas.
@@ -554,7 +676,7 @@ npm run validate:mcp-contracts
 npm run validate:architecture
 ```
 
-This verifies protocol pinning, `catalog.json`/`tools.md`/schema parity, and enforced layering boundaries before CI or release.
+The MCP contracts validator checks: protocol pinning, `catalog.json`/`tools.md`/schema parity, mutating-tool cross-check against `TOOL_BEHAVIOR_METADATA`, AJV schema compilation (draft-07 and 2020-12), orphan schema detection, and `supported_roles` validation. The architecture validator enforces layer dependency rules across 93 classified source files.
 
 ### Tool definitions
 
@@ -578,6 +700,7 @@ This verifies protocol pinning, `catalog.json`/`tools.md`/schema parity, and enf
 | `repo.diff_bundle`       | Return review bundle (stat/full diff/files/latest gate summary)        | No                  | orchestrator                           |
 | `feature.ready_to_merge` | Commit + merge promotion after required gates and approval checks      | Yes                 | orchestrator, system                   |
 | `feature.delete`         | Delete feature runtime artifacts and optional local git/worktree state | Yes                 | orchestrator, system                   |
+| `feature.send_message`   | Send a message to the active agent session for a feature               | Yes                 | orchestrator, system                   |
 | `gates.list`             | List available gate profiles/modes                                     | No                  | orchestrator, builder, qa              |
 | `gates.run`              | Execute gate profile/mode, capture logs/evidence, enforce thresholds   | Yes                 | builder, qa, orchestrator              |
 | `evidence.latest`        | Return latest evidence summary for feature                             | No                  | qa, orchestrator                       |
@@ -586,8 +709,12 @@ This verifies protocol pinning, `catalog.json`/`tools.md`/schema parity, and enf
 | `locks.acquire`          | Acquire/renew resource lease lock for feature                          | Yes                 | orchestrator, system                   |
 | `locks.release`          | Release held resource lock                                             | Yes                 | orchestrator, system                   |
 | `collisions.scan`        | Compute collision matrix across accepted plans                         | No                  | planner, orchestrator                  |
-| `report.dashboard`       | Return global orchestration summary                                    | No                  | orchestrator                           |
+| `report.dashboard`       | Return global orchestration summary (includes cost and PR metadata)    | No                  | orchestrator                           |
 | `report.feature_summary` | Return per-feature state/diff/evidence summary                         | No                  | orchestrator                           |
+| `cost.record`            | Record a cost entry for a feature (token usage, API cost)              | Yes                 | orchestrator, system                   |
+| `cost.get`               | Return accumulated cost for a feature                                  | No                  | orchestrator, system                   |
+| `performance.record_outcome` | Record feature outcome (status, retries, duration, cost) for analytics | Yes             | orchestrator, system                   |
+| `performance.get_analytics`  | Return aggregated performance metrics by provider/model            | No                  | orchestrator, system                   |
 
 ### Role expectations at a glance
 
@@ -601,9 +728,11 @@ This verifies protocol pinning, `catalog.json`/`tools.md`/schema parity, and enf
 
 ## Quality & Testing
 
+## Quality & Testing
+
 - framework: Vitest (`apps/control-plane/vitest.config.ts`)
 - coverage output: `coverage/control-plane`
-- configured thresholds: lines/branches/functions/statements at `90%`
+- configured thresholds: lines/branches/functions/statements at `90%` (enforced per-file)
 - workspace tooling: Nx targets (`run`, `build`, `test`, `typecheck`)
 - Nx launcher: use `npm run nx -- <target>`; this workspace defaults to `NX_DAEMON=false` and `NX_ISOLATE_PLUGINS=false` to avoid Unix-socket worker failures in restricted environments.
 - Shell setup for raw `npx nx` commands:
@@ -619,10 +748,22 @@ This verifies protocol pinning, `catalog.json`/`tools.md`/schema parity, and enf
 From [progress.md](spec-files/progress.md):
 
 - Nx + TypeScript + Vitest migration complete
-- Kernel + supervisor + CLI implemented end-to-end
-- strict linting is enforced (`npm run lint`) and build is lint-gated
-- `npm run typecheck` passes
-- architecture boundary checks are CI-enforced via `npm run validate:architecture`
+- Kernel + supervisor + CLI implemented end-to-end with 12 commands
+- 33 MCP tools registered across 5 roles; all schemas AJV-validated in CI
+- Web dashboard (`packages/web-dashboard/`) with SSE stream, Kanban UI, and review/checkout APIs
+- Notification system (desktop, Slack, webhook, in-process) with 4-tier priority routing
+- Cost tracking and budget enforcement (`cost.json` per feature, `PAUSED_BUDGET` status)
+- Agent performance analytics with aggregates by provider/model
+- Dependency-aware feature scheduling with circular detection and auto-promotion on merge
+- Parallel gate execution with `parallel_group` / `depends_on` wave scheduling
+- CI failure auto-remediation (`reactions-service`) with configurable retry and escalation
+- PR lifecycle integration with merge scoring and `changes_requested` reaction
+- Multi-project support (`multi-project.yaml`, `--project` flag, per-project lease isolation)
+- Hash-based multi-instance isolation (SHA256 instance IDs, namespaced run-lease paths)
+- Linear and Jira issue tracker adapters with full API-backed status sync
+- Architecture boundary checks CI-enforced via `npm run validate:architecture` (93 files, 0 violations)
+- Strict linting enforced (`npm run lint`) and build is lint-gated
+- `npm run typecheck` passes; `npm test` passes (68 test files / 899 tests; all per-file coverage ≥ 90%)
 
 Environment note observed during implementation sessions:
 

package/agentic/orchestrator/adapters.yaml

@@ -0,0 +1,3 @@
+notification-channel: desktop
+activity-detector: claude-jsonl
+scm-provider: github

package/agentic/orchestrator/gates.yaml

@@ -1,4 +1,10 @@
 version: 1
+# Gate commands support {base_branch} interpolation for incremental test selection:
+#   fast: "npx vitest run --changed {base_branch}"  # runs only affected tests
+#   full: "npx vitest run"                            # always runs complete suite
+#
+# Parallel execution: steps with the same `parallel_group` run concurrently.
+# Use `depends_on` to declare ordering constraints between steps.
 profiles:
   default:
     modes:
@@ -23,6 +29,47 @@ profiles:
       coverage_branch_min: 0.9
       coverage_line_target: 1.0
       coverage_branch_target: 1.0
+  parallel_example:
+    modes:
+      fast:
+        - name: lint
+          cmd: ["npx", "eslint", "."]
+          parallel_group: static_checks
+          timeout_seconds: 300
+        - name: typecheck
+          cmd: ["npx", "tsc", "--noEmit"]
+          parallel_group: static_checks
+          timeout_seconds: 300
+        - name: test
+          cmd: ["npx", "vitest", "run", "--changed", "{base_branch}"]
+          depends_on: [lint, typecheck]
+          timeout_seconds: 600
+      full:
+        - name: lint
+          cmd: ["npx", "eslint", "."]
+          parallel_group: static_checks
+          timeout_seconds: 300
+        - name: typecheck
+          cmd: ["npx", "tsc", "--noEmit"]
+          parallel_group: static_checks
+          timeout_seconds: 300
+        - name: test
+          cmd: ["npx", "vitest", "run"]
+          depends_on: [lint, typecheck]
+          timeout_seconds: 1200
+      merge:
+        - name: merge_safety
+          cmd: ["npx", "vitest", "run"]
+          timeout_seconds: 1200
+    parsers:
+      coverage:
+        type: lcov
+        path: coverage/control-plane/lcov.info
+    thresholds:
+      coverage_line_min: 0.9
+      coverage_branch_min: 0.9
+      coverage_line_target: 1.0
+      coverage_branch_target: 1.0
 capabilities:
   - none
   - lcov

package/agentic/orchestrator/policy.yaml

@@ -78,11 +78,37 @@ merge_policy:
     - rebase
 worktree:
   base_branch: main
+  # post_create:  # optional - commands to run after worktree creation
+  #   - "npm ci"
+  # symlinks:  # optional - files to symlink from main repo into each worktree
+  #   - .env
+  #   - .claude
 recovery:
   orchestrator_session_reattach_timeout_ms: 5000
   orphan_session_cleanup_enabled: true
 supervisor:
   max_iterations_per_phase: 6
+  max_parallel_gate_runs: 2
+  agent_idle_threshold_ms: 300000
+cleanup:
+  auto_after_merge: false
+  grace_period_seconds: 3600
+notifications:
+  enabled: false
+  channels:
+    desktop:
+      enabled: false
+    slack:
+      enabled: false
+      webhook: ""
+      channel: "#aop-alerts"
+    webhook:
+      enabled: false
+      url: ""
+  routing:
+    critical: [desktop, slack]
+    warning: [slack, desktop]
+    info: [slack]
 rbac:
   orchestrator:
     - feature.discover_specs
@@ -113,6 +139,11 @@ rbac:
     - report.feature_summary
     - feature.ready_to_merge
     - feature.delete
+    - feature.send_message
+    - cost.record
+    - cost.get
+    - performance.record_outcome
+    - performance.get_analytics
   planner:
     - feature.get_context
     - feature.state_get
@@ -121,6 +152,7 @@ rbac:
     - collisions.scan
     - repo.read_file
     - repo.search
+    - performance.get_analytics
   builder:
     - feature.get_context
     - feature.state_get
@@ -130,6 +162,7 @@ rbac:
     - repo.read_file
     - repo.search
     - gates.run
+    - performance.get_analytics
   qa:
     - feature.get_context
     - feature.state_get
@@ -141,5 +174,61 @@ rbac:
     - evidence.latest
     - qa.test_index_get
     - qa.test_index_update
+    - performance.get_analytics
   system:
     - "*"
+
+dashboard:
+  enabled: true
+  port: 3000
+reactions:
+  gate_failed:
+    enabled: true
+    max_retries: 2
+    action: retry_with_agent_repair
+    escalate_after: 2
+    retry_delay_ms: 30000
+  agent_stuck:
+    enabled: true
+    action: notify_only
+    idle_threshold_ms: 300000
+    escalate_after: 2
+  collision_detected:
+    enabled: true
+    action: notify_only
+  ready_to_merge:
+    enabled: true
+    action: notify_only
+  changes_requested:
+    enabled: false
+    action: send_review_context_to_agent
+    escalate_after: 2
+
+budget:
+  per_feature_limit_usd: 50.00
+  alert_threshold: 0.8
+
+issue_tracker:
+  enabled: false
+  type: github
+  config:
+    repo: ""
+  # linear example:
+  # enabled: true
+  # type: linear
+  # config:
+  #   token: "${LINEAR_API_TOKEN}"
+  #   base_url: "https://api.linear.app/graphql"
+  #   state_id_backlog: ""
+  #   state_id_in_progress: ""
+  #   state_id_in_review: ""
+  #   state_id_done: ""
+  # jira example:
+  # enabled: true
+  # type: jira
+  # config:
+  #   base_url: "https://your-org.atlassian.net"
+  #   email: "bot@example.com"
+  #   token: "${JIRA_API_TOKEN}"
+  #   transition_in_progress: "In Progress"
+  #   transition_done: "Done"