main has the recall source + hooks.json wiring (from #65) but never got
the built bundles, so UserPromptSubmit -> recall-hook.cjs errored with
MODULE_NOT_FOUND on every turn. This commits the build output:
- recall-hook.cjs, recall-approve.cjs (new) — the two missing bundles
hooks.json already references
- context-hook/summary-hook/add-memory/save-project-memory/search-memory/
status .cjs (refreshed) — were stale on main (built pre-#65), so they
reported version 0.0.7 while the source is 0.0.8; rebuilding aligns them
(also clears the false "update available" notice loop)
No package/version files changed — source is already at 0.0.8; this only
ships the bundles that build.js produces.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Resolve by rebuilding plugin/scripts/*.cjs so the artifacts carry BOTH
main's source changes (Windows auth fix, update-notice via version-check)
and this branch's recall hooks — the .cjs were otherwise stale against the
merged source. Apply biome auto-format to the inherited context-hook.js /
version-check.js so `biome ci` passes.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a UserPromptSubmit hook that injects a directive telling Claude to
reason — per message — about whether recalling memory would help, and
only then search via the supermemory-search skill. A PreToolUse hook
auto-approves that search so it runs silently, like auto-capture, instead
of interrupting with a permission prompt.
Reasoned recall and auto-approve are built-in (no toggles): searching
only when it helps keeps more usage on the user's plan. The auto-approve
is scoped to the read-only search and refuses any command laced with
shell chaining/redirection. SUPERMEMORY_DEBUG surfaces a per-turn
[recall-decision] line for debugging. SessionStart profile load and the
Stop-hook save are unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Use git remote URL instead of folder name for consistent repo container tags
- Use `git remote get-url origin` to derive repo name for container tags instead of relying solely on folder name
- Adds `getGitRepoName()` function to extract repo name from git remote URL
- Falls back to folder name if no remote is configured
- Extract repo name from git remote get-url origin instead of directory path
- Makes container tags consistent across team members with different local paths
- Falls back to directory name if no git remote
- Updated README: streamlined docs, added config tables
Refresh plugin architecture with Supermemory
- Add project-level configuration system (.claude/.supermemory-claude/config.json) for per-repo API keys and container tags
- Add /project-config command to manage project settings
- Add /super-save skill for saving project knowledge (architectural decisions, bug fixes, design patterns)
- Add repo container tag support for team-shared memories (separate from personal memories)
- Rename prompt-hook to save-project-memory with dedicated repo-level memory saving
- Remove observation hook (consolidate into other hooks)
- Enhance context hook, search memory, and summary hook scripts
- Update supermemory client with repo entity context support
- Remove MCP config file
feat: add /claude-supermemory:index command for codebase indexing
Changes:
- Add /claude-supermemory:index command to explore and index codebase into Supermemory
- Add add-memory.js script for saving compiled findings
- Update build.js to include add-memory in build
- Remove unused settings (maxContextMemories, maxProjectMemories)
- Update README with new command documentation
Add browser-based authentication flow
Major:
1. Browser-based auth flow - auto-opens browser for login, no manual API key setup
2. Credentials persistence in ~/.supermemory-claude/credentials.json
3. Localhost callback server to receive API key from auth page
Medium:
4. Configurable URLs via SUPERMEMORY_AUTH_URL and SUPERMEMORY_API_URL env vars
5. Styled success/error pages matching Supermemory branding
Minor:
6. Logout script (src/logout.js) for clearing credentials
1. Bundled Scripts — Used esbuild to bundle all dependencies into self-contained .cjs files. Users don't need npm install.
2. Session-Based Memory — One document per session using sessionId as customId. All hooks append to same document.
3. Fixed Double Shebang — Source files had shebang + esbuild added another. Removed from source, esbuild adds via banner.
4. Code Cleanup — Removed unnecessary comments and spacing. Clean source in src/, built output in plugin/scripts/.
5. Simplified README — Removed MCP, architecture, comparisons. Kept installation and config only.
ved015