compound-agent 2.7.0 → 2.7.2

package/CHANGELOG.md

@@ -7,6 +7,45 @@ 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).
 
+## [Unreleased]
+
+## [2.7.2] - 2026-04-16
+
+### Added
+
+- **`ca uninstall` command**: reverses `ca init` / `ca setup` in three tiers. Default removes managed Claude Code hooks from `.claude/settings.json`. `--templates` additionally removes the `compound/` template directories (`.claude/agents/compound/`, `.claude/commands/compound/`, `.claude/skills/compound/`, `docs/compound/`) and `.claude/plugin.json`. `--all` additionally removes `.compound-agent/` runtime state and strips managed marker blocks from `AGENTS.md`, `.claude/CLAUDE.md`, root `.gitignore`, and `.claude/.gitignore`. `.claude/lessons/` and `.claude/compound-agent.json` are ALWAYS preserved. Requires `--yes` to skip interactive confirmation.
+- **Install profiles (`ca setup --profile <minimal|workflow|full>`)**: `minimal` installs only lesson-capture plumbing (lessons dir, AGENTS.md integration, plugin.json, and 3 hooks — SessionStart/PreCompact prime + UserPromptSubmit reminder) — no commands, no phase skills, no agent role skills, no docs. `workflow` adds the 5-phase cook-it workflow (all commands, phase skills, agent role skills, doc templates, all phase/failure hooks) but skips the `docs/compound/research/` tree. `full` (default, backward-compatible) installs everything. `--confirm-prune` is required when a lower profile would delete existing templates on disk.
+
+### Changed
+
+- **Default model bumped to Opus 4.7**: All default model references updated from `claude-opus-4-6[1m]` to `claude-opus-4-7[1m]`. Affects `ca loop --model`, `ca loop --review-model`, `ca polish --model`, `ca improve --model`, the `claude-opus` reviewer selector in the generated review/polish scripts, and the Simplicity lens in the architect advisory fleet. Template skills (`loop-launcher/SKILL.md`, `architect/references/infinity-loop/README.md`, `architect/references/infinity-loop/troubleshooting.md`, `architect/references/polish-loop/README.md`, `architect/references/advisory-fleet.md`) and shipped docs (`CLI_REFERENCE.md`) updated to match. The Windows PowerShell reference template `$MODEL` default also updated.
+
+### Fixed
+
+- **Concrete fallback quality-gate commands**: when the project stack cannot be detected, the fallback strings substituted for `{{QUALITY_GATE_TEST}}`, `{{QUALITY_GATE_LINT}}`, and `{{QUALITY_GATE_BUILD}}` are now shell commands that exit non-zero with a `[compound-agent]`-tagged diagnostic on stderr, e.g. `sh -c 'echo "[compound-agent] test command not configured..." >&2; exit 1'`. Previously the fallbacks were English prose ("detect and run the project's test suite") that, when rendered into SKILL.md as shell commands, broke sh parsing on the apostrophe and produced a confusing error rather than a clear failure. Agents now see a visible failure with actionable configuration guidance.
+- **`hasTransitionEvidence` robustness**: replaced hardcoded `5` with `len(Phases)` so the cook-it final-phase branch tracks the phase list automatically. No behavioral change today (architect at index 6 correctly falls through); regression tests (`TestHasTransitionEvidence_OutOfRangeReturnsFalse`, `TestHasTransitionEvidence_FinalPhaseAlwaysTrue`) pin the contract so a future `Phases` shrink can't introduce a panic.
+- **Empty hook arrays in `settings.json`**: `AddHooksForProfile` and `RemoveAllHooks` both drop empty `"PreToolUse": []` style entries at the end of their run (previously created eagerly by `upgradeNpxHooks` calling `getHookArray` for every known hook type). Cosmetic only; no behavioral change for in-profile hooks.
+- **`removeIfPresent` (formerly `removeIfExists`) semantics**: rewrote to suppress `os.ErrNotExist` internally and return `(existed bool, err error)`. `uninstallTemplates` now propagates real I/O errors (permission denied, read-only FS) when removing `.claude/plugin.json` instead of silently reporting success. Previously a permission error on plugin.json would make `ca uninstall --templates` report success without removing the file — flagged by the second-pass reviewer as a blocking issue. Regression tests `TestRemoveIfPresent_RealIOErrorSurfaces` and `TestUninstallTemplates_PropagatesRealIOError` pin the contract.
+- **`polish-loop.sh` dry-run leaked state** (#17, #16): `POLISH_DRY_RUN=1` now fully skips the post-loop commit/push block AND writes a distinct `"status":"dry-run-completed"` to `.polish-status.json` instead of overwriting it with `"status":"completed"`. Previously a dry run still mutated git *and* produced a status file indistinguishable from a real run, defeating the preflight contract and misleading any monitoring tool that polled the status file. Regression test `TestPolishCommand_PostLoopRespectsDryRun` pins the guard structure so this can't silently come back.
+
+## [2.7.1] - 2026-04-10
+
+### Added
+
+- **Surface alignment reviewer**: New agent-role-skill that verifies cross-layer connectivity (frontend↔backend↔database↔API). Checks regenerate-and-diff compliance, architecture test presence, database testing fidelity, schema evolution safety, and auth surface coverage. Spawned for medium and large diffs during review phase.
+- **P16 "Surfaces stay connected"**: New principle in the agentic audit/setup manifesto (Pillar II). Scores projects on cross-layer integration testing maturity (0-2). Updated overall scoring from 30→32.
+- **5 deep research documents** shipped with the library: architecture tests (ArchUnit survey), regenerate-and-diff patterns, database testing patterns, test infrastructure as code, and protobuf schema evolution. Mapped to specific reviewer agents for calibrated reviews.
+- **Research-calibrated review fleet**: Review skill now includes surface-alignment-reviewer in medium+ tier (9 reviewers), with calibration query for surface alignment lessons. Lesson-calibration references updated with all 5 research doc mappings.
+
+### Changed
+
+- **build-great-things**: Added "System coherence is craft" as third design philosophy foundation. New structural coherence section in mandatory quality checklist (6 items). Added laziness pattern #13 "Disconnected layers".
+- **Existing reviewers enhanced**: drift-detector, test-coverage-reviewer, and architecture-reviewer now reference relevant research documents. test-coverage-reviewer distinguishes integration from unit tests and flags SQLite substitution.
+
+### Fixed
+
+- **Dependencies**: `modernc.org/sqlite` 1.48.0→1.48.1 (fixes memory leaks and double-free in multi-statement queries), `libc` 0.2.183→0.2.184 (patch bump of transitive Rust dependency).
+
 ## [2.7.0] - 2026-04-09
 
 ### Changed

package/README.md

@@ -310,7 +310,7 @@ The CLI binary is `ca` (alias: `compound-agent`).
 | `ca loop --review-every <n>` | Review every N completed epics (0 = end-only, default: 0) |
 | `ca loop --max-review-cycles <n>` | Max review/fix iterations (default: 3) |
 | `ca loop --review-blocking` | Fail loop if review not approved after max cycles |
-| `ca loop --review-model <model>` | Model for implementer fix sessions (default: claude-opus-4-6[1m]) |
+| `ca loop --review-model <model>` | Model for implementer fix sessions (default: claude-opus-4-7[1m]) |
 | `ca improve` | Generate improvement loop script from `improve/*.md` programs |
 | `ca improve --topics <names...>` | Run only specific topics |
 | `ca improve --max-iters <n>` | Max iterations per topic (default: 5) |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "compound-agent",
-  "version": "2.7.0",
+  "version": "2.7.2",
   "type": "module",
   "description": "Learning system for Claude Code — avoids repeating mistakes across sessions",
   "bin": {
@@ -51,12 +51,12 @@
     "knowledge-management"
   ],
   "optionalDependencies": {
-    "@syottos/darwin-arm64": "2.7.0",
-    "@syottos/darwin-x64": "2.7.0",
-    "@syottos/linux-arm64": "2.7.0",
-    "@syottos/linux-x64": "2.7.0",
-    "@syottos/win32-x64": "2.7.0",
-    "@syottos/win32-arm64": "2.7.0"
+    "@syottos/darwin-arm64": "2.7.2",
+    "@syottos/darwin-x64": "2.7.2",
+    "@syottos/linux-arm64": "2.7.2",
+    "@syottos/linux-x64": "2.7.2",
+    "@syottos/win32-x64": "2.7.2",
+    "@syottos/win32-arm64": "2.7.2"
   },
   "author": "Nathan Delacrétaz",
   "license": "MIT",