`ai@5` was a hard dependency, so apps on AI SDK 6 or 7 got a second copy and our tools failed to typecheck in `generateText`/`streamText`. `withSupermemory` also rejected AI SDK 7 models (`specificationVersion: "v4"`).
- `ai` is now an optional peer (`^5 || ^6 || ^7`); `@ai-sdk/provider` peer allows `^4`.
- `withSupermemory` accepts v4 models.
- `@ai-sdk/openai` and `@ai-sdk/anthropic` move to devDependencies; `src` never imported them.
- New `test:compat` packs the build and typechecks + runs it against ai 5, 6 and 7. Runs on tools PRs and before publish.
Every integration (AI SDK, OpenAI, Mastra, VoltAgent, Claude memory) now calls v5 through `supermemory@5`. The config takes one `namespace` instead of `containerTags` or `projectId`, and `withSupermemory` takes `namespace` and `id` instead of `containerTag` and `customId`. No aliases. With no config the tools still use `sm_project_default`.
Conversations are stored as one document per conversation keyed by `id` instead of `/v4/conversations`. `memoryForget` drops `reason`; forgetting by text previews with `forgetMatching` and then forgets exact matches by id. Claude memory marks its files with `metadata.source` instead of a second tag. Search keeps the 2.x defaults so results do not shift.
`packages/ai-sdk` is removed: npm already deprecates it in favor of `@supermemory/tools/ai-sdk`, so its CI steps and playground wiring go too. `apps/sdk-playground` moves to the new tools API and v5 routes, including its Python server.
Tested against production: add, search, profile, list and delete. 112 unit tests pass; type errors drop from 148 to 141, none new. The `supermemory` dependency pins the rc until 5.0.0 is published.
## Summary
The `workflow_run` auto-fix job has write permissions and checks out the triggering PR branch. It now runs only when all three conditions hold:
- the tracked CI workflow failed on a pull request;
- the pull request branch belongs to this repository, not a fork;
- the triggering actor is not a bot account.
The same-repository check closes the privileged fork boundary. The generic `[bot]` suffix check covers Polylane, Graphite, Dependabot, and other GitHub App bot users without maintaining a name list.
## Validation
- `go run github.com/rhysd/actionlint/cmd/actionlint@v1.7.12 .github/workflows/claude-auto-fix-ci.yml`
- YAML parse with the repository's installed parser
- Final diff audit: one workflow, +3/-1, no added comments
Human-triggered same-repository pull requests keep the existing auto-fix behavior.
## Summary
- Add `apps/sdk-playground` — chat UI to test TS/Python SDK integrations
- Context panel with document memories, API keys in dashboard, tools reference tab
- Python FastAPI server on port 8792; portless entry in `portless.json`
Stacked on #1436
## Test plan
- [ ] `cd apps/sdk-playground && bun run check-types`
- [ ] `bun run dev` with Supermemory + OpenAI keys in UI
- [ ] Switch SDKs and verify chat + context panel
Made with [Cursor](https://cursor.com)
## Summary
- Add tools/ai-sdk unit test jobs to `ci.yml`
- Update `turbo.json` and root `package.json` scripts
- Refresh `bun.lock`
Stacked on #1435
## Test plan
- [ ] CI passes on this branch
Made with [Cursor](https://cursor.com)
## Summary
- Re-export full tool set from `@supermemory/tools/ai-sdk`
- Add unit tests for tool re-exports
Stacked on #1432
## Test plan
- [ ] `bun run test:unit` in `packages/ai-sdk`
Made with [Cursor](https://cursor.com)
## Summary
- Refresh canonical tool descriptions in `tools-shared.ts`
- Align OpenAI and AI SDK tool bindings with 7-tool surface
- Export `TOOL_DESCRIPTIONS` / `PARAMETER_DESCRIPTIONS` from package index
Stacked on #1431
## Test plan
- [ ] `bun run test:unit` in `packages/tools`
Made with [Cursor](https://cursor.com)
Add CI and upgrade Claude workflows
No CI existed — type errors and lint issues only caught by Cloudflare builds. Added type check + biome lint CI on PRs, auto-fix workflow when CI fails, and
upgraded code review with supermemory MCP + inline comments.
