compound-agent 2.1.2 → 2.2.1

package/CHANGELOG.md

@@ -7,6 +7,41 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [2.2.1] - 2026-03-24
+
+### Added
+
+- **Loop generator production parity**: Brought the Go `ca loop` script generator to full parity with the hardened production `infinity-loop.sh`. Ported crash handler (EXIT trap with status file logging), 3-layer memory safety (repo-scoped orphan cleanup, memory gate, background watchdog with PID tracking), `parse_json()` with jq/python3 fallback, dependency-aware epic ordering (`check_deps_closed()`), dual-file anchored marker detection, and CLI prerequisite checks.
+- **Loop review and improve phases**: Implemented 8 missing flags from the former TS CLI: `--reviewers`, `--review-every`, `--max-review-cycles`, `--review-blocking`, `--review-model`, `--improve`, `--improve-max-iters`, `--improve-time-budget`. Review phase supports multi-model spawning, session management, and review cycles with implementer fix loop. Improve phase supports topic discovery, iteration with rollback, and time budget.
+- **Field-tested enhancements**: Git status check after epic completion (auto-commits if dirty), git push at loop end (with remote availability check), reviewer availability summary logging.
+- **Infinity-loop reference docs**: Added troubleshooting section and real-world example from compound-agent's own 6-epic loop run.
+
+### Fixed
+
+- **Review triggers were dead code**: Review phase triggers were placed after an exit statement and never executed.
+- **Undefined variable in periodic trigger**: `$RESULT` replaced with `$SUCCESS` in periodic review trigger.
+- **Review base SHA reset in loop**: `REVIEW_BASE_SHA` was incorrectly reset inside the while loop on every iteration.
+- **Improve phase stdin piping**: `extract_text` was using file args instead of stdin pipe.
+- **Conditional exit**: Exit line now omitted when improve phase follows review phase.
+
+## [2.2.0] - 2026-03-23
+
+### Added
+
+- **CLI flag parity with TypeScript**: Ported 5 missing flags from the former TS CLI to the Go implementation for full migration parity:
+  - `--quiet` / `-q` global flag — suppresses non-essential `[ok]`/status output in `init` and `setup`
+  - `init --skip-agents` — skips template installation (AGENTS.md, skills, commands, docs)
+  - `init --skip-claude` — skips Claude Code hooks installation (alias for `--skip-hooks`)
+  - `setup claude --dry-run` — previews what would be installed/upgraded/reconciled without writing
+  - `download-model --json` — outputs download result as JSON
+- **Stack-aware quality gates**: `ca setup` now detects the project stack (Go, Rust, Python, Node, Make) and substitutes `{{QUALITY_GATE_TEST}}` / `{{QUALITY_GATE_LINT}}` placeholders in skill and doc templates with the correct commands. Non-JS codebases no longer see hardcoded `pnpm test` / `pnpm lint`.
+
+### Changed
+
+- **Refactored `main.go`**: Extracted `buildHooksCmd()` helper from `main()` to stay within 50-line function limit.
+- **Refactored `commands_setup.go`**: Extracted `setupClaudeOpts` struct and `runSetupClaude()` function from the `registerSetupClaudeCmd` inline closure.
+- **Refactored `commands_advanced.go`**: Extracted `printDownloadModelResult()` helper from `downloadModelCmd`.
+
 ## [2.1.2] - 2026-03-23
 
 ### Fixed

package/README.md

@@ -4,7 +4,7 @@
 
 [![npm version](https://img.shields.io/npm/v/compound-agent)](https://www.npmjs.com/package/compound-agent)
 [![license](https://img.shields.io/npm/l/compound-agent)](LICENSE)
-[![TypeScript](https://img.shields.io/badge/TypeScript-5.3+-blue)](https://www.typescriptlang.org/)
+[![Go](https://img.shields.io/badge/Go-1.24+-00ADD8)](https://go.dev/)
 
 <p align="center">
   <img src="docs/assets/diagram-4.png" alt="Compound-agent ecosystem overview: Architect phase decomposes work via Socratic dialogue into a dependency graph. ca loop chains tasks with cross-model review, retry, and fresh sessions. Scenario evaluation validates changes with iterative refinement. All backed by persistent memory (lessons + knowledge across all sessions) and verification gates (tests, lint, type checks on every task)." width="700">
@@ -342,11 +342,14 @@ The CLI binary is `ca` (alias: `compound-agent`).
 | `ca setup` | One-shot setup (hooks + templates) |
 | `ca setup --skip-hooks` | Setup without installing hooks |
 | `ca setup --json` | Output result as JSON |
-| `ca setup --repo-root <path>` | Specify repository root |
 | `ca setup claude` | Install Claude Code hooks only |
 | `ca setup claude --status` | Check Claude Code integration health |
 | `ca setup claude --uninstall` | Remove Claude hooks only |
+| `ca setup claude --dry-run` | Preview what would change without writing |
 | `ca init` | Initialize compound-agent in current repo |
+| `ca init --skip-agents` | Skip AGENTS.md and template installation |
+| `ca init --skip-claude` | Skip Claude Code hooks installation |
+| `ca download-model --json` | Download embedding model with JSON output |
 | `ca about` | Show version, animation, and recent changelog |
 | `ca doctor` | Verify external dependencies and project health |
 
@@ -394,32 +397,23 @@ A: The loop works and has been used to ship real projects, including compound-ag
 ## Development
 
 ```bash
-pnpm install          # Install dependencies
-pnpm build            # Build with tsup
-pnpm dev              # Watch mode (rebuild on changes)
-pnpm lint             # Type check + ESLint
+cd go && go build -tags sqlite_fts5 ./cmd/ca   # Build CLI binary
+cd go && go test -tags sqlite_fts5 ./...        # Full test suite
+cd go && go vet -tags sqlite_fts5 ./...         # Static analysis
 ```
 
-| Script | Duration | Use Case |
-|--------|----------|----------|
-| `pnpm test:fast` | ~12s | Rapid feedback during development |
-| `pnpm test` | ~60s | Full suite before committing |
-| `pnpm test:changed` | varies | Only tests affected by recent changes |
-| `pnpm test:watch` | - | Watch mode for TDD workflow |
-| `pnpm test:all` | ~60s | Full suite with model download |
-
 ## Technology Stack
 
 | Component | Technology |
 |-----------|------------|
-| Language | TypeScript (ESM) |
-| Package Manager | pnpm |
-| Build | tsup |
-| Testing | Vitest + fast-check (property tests) |
-| Storage | better-sqlite3 + FTS5 |
-| Embeddings | @huggingface/transformers + nomic-embed-text-v1.5 (Q8 ONNX) |
-| CLI | Commander.js |
-| Schema | Zod |
+| Language | Go |
+| Package Manager | Go modules (+ pnpm for npm wrapper) |
+| Build | go build with CGO + sqlite_fts5 tag |
+| Testing | go test + table-driven tests |
+| Storage | mattn/go-sqlite3 + FTS5 |
+| Embeddings | ca-embed (Rust daemon via IPC) |
+| CLI | Cobra |
+| Release | GoReleaser |
 | Issue Tracking | Beads (bd) |
 
 ## Documentation

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "compound-agent",
-  "version": "2.1.2",
+  "version": "2.2.1",
   "type": "module",
   "description": "Learning system for Claude Code — avoids repeating mistakes across sessions",
   "bin": {
@@ -50,10 +50,10 @@
     "knowledge-management"
   ],
   "optionalDependencies": {
-    "@syottos/darwin-arm64": "2.1.2",
-    "@syottos/darwin-x64": "2.1.2",
-    "@syottos/linux-arm64": "2.1.2",
-    "@syottos/linux-x64": "2.1.2"
+    "@syottos/darwin-arm64": "2.2.1",
+    "@syottos/darwin-x64": "2.2.1",
+    "@syottos/linux-arm64": "2.2.1",
+    "@syottos/linux-x64": "2.2.1"
   },
   "author": "Nathan Delacrétaz",
   "license": "MIT",