feat: add gbrain check-update command and auto-update agent workflow (#15)

* feat: add `gbrain check-update` command for auto-update notifications

Deterministic collector that checks GitHub Releases for new versions,
compares semver (minor+ only, skips patches), and fetches changelog diffs.
Exports `detectInstallMethod()` from upgrade.ts for reuse. Includes 15
unit tests covering version comparison, CLI wiring, and error handling.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* test: add E2E upgrade tests against real GitHub API

Exercises check-update CLI end-to-end: valid JSON output, human-readable
mode, help text, graceful no-releases handling, and version comparison
wiring. Skips gracefully when network is unavailable.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: add SKILLPACK Section 17 — auto-update notifications

Full agent playbook for the update lifecycle: check, notify, consent,
upgrade, skills refresh, schema sync, report. Includes standalone
self-update for skillpack-only users via version markers and raw
GitHub URL fetching. Adds version markers to both SKILLPACK and
RECOMMENDED_SCHEMA headers.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: add auto-update step 7 to install paste, setup Phase G, migrations dir

Adds step 7 to the OpenClaw install paste (default-on update checks).
Setup skill gets Phase G (conditional offer for manual installs) and
schema state tracking via ~/.gbrain/update-state.json. Creates
skills/migrations/ directory for version-specific upgrade directives.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: update CLAUDE.md with E2E test DB lifecycle, migration conventions

Adds E2E test DB lifecycle instructions (spin up, run, tear down).
Documents version migration convention (skills/migrations/v[version].md)
and schema state tracking (~/.gbrain/update-state.json). Updates test
file counts.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: broken semver comparison in extractChangelogBetween

The version range check compared minor versions without guarding on
major being equal, causing incorrect changelog entries to be captured
(e.g., v0.5.0 would match when upgrading from v1.2.0). Extracted
semverGt/semverLte helpers for correct comparisons. Added 5 tests
for extractChangelogBetween covering cross-major, same-version, and
malformed input cases.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v0.4.1)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

skills/setup/SKILL.md

@@ -208,10 +208,39 @@ output. It checks connection, pgvector, RLS, schema version, and embeddings.
 | No pages found | Query before import | Import files into gbrain first |
 | RLS not enabled | Security gap | Run `gbrain init` again (auto-enables RLS) |
 
+## Phase G: Auto-Update Check (if not already configured)
+
+If the user's install did NOT include setting up auto-update checks (e.g., they
+used the manual install path or an older version of the OpenClaw paste), offer it:
+
+> "Would you like daily GBrain update checks? I'll let you know when there's a
+> new version worth upgrading to — including new skills and schema recommendations.
+> You'll always be asked before anything is installed."
+
+If they agree:
+1. Test: `gbrain check-update --json`
+2. Register daily cron (see GBRAIN_SKILLPACK.md Section 17)
+
+If already configured or user declines, skip.
+
+## Schema State Tracking
+
+After presenting the recommended directories (Phase C/E) and the user selects which
+ones to create, write `~/.gbrain/update-state.json` recording:
+- `schema_version_applied`: current gbrain version
+- `skillpack_version_applied`: current gbrain version
+- `schema_choices.adopted`: directories the user created
+- `schema_choices.declined`: directories the user explicitly skipped
+- `schema_choices.custom`: directories the user added that aren't in the recommended schema
+
+This file enables future upgrades to suggest new schema additions without
+re-suggesting things the user already declined.
+
 ## Tools Used
 
 - `gbrain init --non-interactive --url ...` -- create brain
 - `gbrain import <dir> --no-embed [--workers N]` -- import files
 - `gbrain search <query>` -- search brain
 - `gbrain doctor --json` -- health check
+- `gbrain check-update --json` -- check for updates
 - `gbrain embed refresh` -- generate embeddings