- New "SDKs, tools and the CLI" section: TypeScript SDK is v5 from
5.0.0-rc.5 (earlier RCs still v3/v4), Python SDK and @supermemory/tools
still on v3/v4, CLI and `supermemory local` unaffected; v4 -> v5 SDK
call map and dropped methods, linking the SDK's MIGRATION.md
- Link /v5/reference and /reference to api.supermemory.ai
- List conversation ingestion and container-tag merges as having no v5
replacement
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The server is stateless HTTP, so every tool call landed in its own PostHog session. Enable conversation ids and let $mcp_conversation_id and $session_id through the metadata filter so echoed handles group calls.
## Summary
- Instrument the MCP v2 server with the pinned PostHog MCP Analytics SDK and replace the custom `mcp_tool_executed` wrapper with standard `$mcp_*` events.
- Send only allowlisted metadata, disable schema injection and exception autocapture, and use personless user IDs with person-profile processing disabled.
- Deliver events through immediate capture guarded by Cloudflare `waitUntil`.
## Verification
- The initial implementation passed the MCP typecheck, existing unit suite, Biome, and Wrangler dry-run bundle.
- A local `who_am_i` MCP call returned successfully and emitted a metadata-only `$mcp_tool_call` on the initial implementation.
- All five checks passed on the final `54a2384` head, including the Cloudflare MCP build.
Actual PostHog ingestion is not verified yet; this workspace still needs a PostHog project token and authenticated Supermemory MCP credential.
Document-to-memory links and actual `derives` relations were both emitted as `derives`, so they shared the same color and legend entry.
This separates structural document links into a `document` edge type, adds a dedicated theme color with `--graph-edge-document` support, and updates force-layout and level-of-detail handling to preserve existing structural behavior. The package and MCP widget legends/themes now distinguish document links from derived-memory relations.
Adds regression coverage for edge classification and validates the package plus its MCP consumer.
<!-- capy-badge:start -->
<a href="https://capy.ai/thread/jam_01M36F4MPFXZCA8J14T53YY029"><picture><source media="(prefers-color-scheme: dark)" srcset="https://capy.ai/badge/accent-dark.svg"><source media="(prefers-color-scheme: light)" srcset="https://capy.ai/badge/accent-light.svg"><img alt="Open in Capy" src="https://capy.ai/badge/accent-light.svg"></picture></a>
<!-- capy-badge:end -->
## Stack context
This is the second PR in the V5 documentation stack, on top of the versioned API reference.
## What and why
Add an agent-oriented V3/V4 to V5 migration guide covering document ingestion and updates, content management, search, profiles, forgetting, namespaces, organization settings, typed filters, and rollout verification. Shared snippets keep the comprehensive guide and focused topic pages consistent.
```mermaid
flowchart LR
Legacy[Legacy integration inventory] --> Mapping[Domain migration guidance]
Mapping --> V5[V5 requests and response readers]
V5 --> Verify[Side-by-side verification and rollout]
```
## Validation
- Verified all 11 migration navigation entries resolve to authored pages.
- Verified all imports across 23 migration and snippet files resolve.
- `git diff --check` passed.
- Mintlify build validation passed against the local generated V5 OpenAPI snapshot.
## Impact
Documentation only. The guide explicitly covers changed defaults, removed operations, partial failures, namespace isolation, and rollback-oriented side-by-side testing.
## Stack context
This is the first PR in the V5 documentation stack. The migration guide and local-development wrapper build on it.
## What and why
Add Legacy and Latest versions to the API Reference navigation, organize all V5 operations by user workflow, and introduce concise overview pages for each domain. The Latest reference consumes the authoritative `/v5/openapi` document published by the Mono API stack.
```mermaid
flowchart LR
Legacy[Legacy V3/V4 OpenAPI] --> Selector[Reference version selector]
V5[V5 OpenAPI] --> Selector
Selector --> Pages[Version-specific endpoint pages]
```
The `GET /ns` compatibility alias remains in the OpenAPI document but is intentionally omitted from navigation in favor of `GET /namespaces`.
## Validation
- Parsed `docs.json` successfully with `jq`.
- Compared navigation against the generated V5 schema: 22 displayed operations, 23 schema operations, with only `GET /ns` intentionally omitted.
- Mintlify build validation passed against the local generated V5 OpenAPI snapshot.
## Deployment dependency
The committed source is `https://api.supermemory.ai/v5/openapi`, which returns 404 until Mono PR #3306 and its API stack are deployed. Merge this PR after that endpoint is live.
## Summary
The billing guide omits Max and contradicts the pricing page about Gmail access. Add Max ($100/month with $130 in monthly credits), correct the plan feature matrix, list all six current coding plugins as available on Free with credit-consuming usage, and update both remaining Scale-only requirements on the Gmail connector page to Max or above.
Clarify that paid-plan automatic top-up limits cap automatic credit purchases, not the total invoice, and correct the documented auto-topup update endpoint from PATCH to POST.
Companion website changes: https://github.com/supermemoryai/landing-2/pull/32
## Validation
- Compared prices, credit inclusions, connector gates, and top-up behavior with the console and API source on main. Verified that all six coding plugins are on FREE_TIER_PLUGIN_IDS and the authentication route bypasses the generic Pro gate for them. Usage still consumes plan credits.
- Checked Markdown table column counts and required Max entries; `git diff --check` passed.
- Confirmed the Gmail introduction, prerequisite, and troubleshooting requirement consistently say Max or above.
- Documentation-only change. A full Mintlify build was not run.
Crawler-access verification, AI-search benchmarking, and analytics/measurement work are excluded from this PR.
chore(web): reduce the app to a redirect shell, drop the browser extension
app.supermemory.ai now forwards everything to the console: plugin, OAuth and invite paths get an immediate 308 with the query intact, everything else shows a short notice first. Removes the browser extension workspace.
chore(web): give the moved notice a proper design
Hostnames become the headline, one primary action, a draining line for the countdown, DM Sans and the dot-grid backdrop from the brand.
chore(docs): point docs and README at the console, drop stale sections
Docs and both READMEs now link to console.supermemory.ai for API keys. Removed the company-brain docs tab with a redirect, and trimmed the README app section.
chore(web): give the redirect five seconds
getDocument filtered on the caller's active space, so an ID from listDocuments in any other space returned "Document not found". With activeSpace unset the fallback is sm_project_default, which broke most cross-space reads.
The API already scopes document reads to the caller's org, so the extra filter added no protection. Verified locally against the mono API: own-space and cross-space IDs now resolve, foreign-org IDs still 404.
Ship dedicated integration docs and point the plugin catalog at them. Grok Bot stays to install, auth, and skills — no Cursor-only config or repo tags.
## Stack Context
Part 3 (top) of a 3-PR stack moving memory deduplication into the SDKs. See `sdk-dedup/tools-ts` for full context.
## What?
Update the SDK playground so its debug view reflects the SDK-owned memory block.
- Displays the current deduplicated `<supermemory>` replacement block produced by the SDK middleware, instead of the old browser-side "seen facts" delta.
- Adds a `memory-dedupe` helper and ignores local `*.tsbuildinfo`.
## Why?
The previous debug cards were misleading — they showed an incremental browser-filtered delta while the middleware actually re-injected the full profile. Now the visualization matches what the SDK really sends.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Low Risk**
> Playground-only visualization and chat gating changes; no production SDK or API behavior.
>
> **Overview**
> The playground **debug trace** now shows the **deduplicated memory block** the SDK middleware would inject (static → dynamic → search, mode-aware), instead of a misleading browser-side “new facts” delta. A new **`memory-dedupe`** helper mirrors `@supermemory/tools` middleware behavior and is applied when fetching container context and building middleware memory debug entries; the context preview card is relabeled to reflect that each turn **replaces** the prior `<supermemory>` block.
>
> **Chat UX:** messaging is enabled when API keys are configured on the **server** (`hasSupermemoryKey` / `hasOpenAiKey` from `/api/chat`), not only when keys are typed in the panel. The message input stays editable while waiting for text; Send still requires non-empty input.
>
> Also ignores `*.tsbuildinfo` in `.gitignore`.
>
> <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit ed15364eb3. Bugbot is set up for automated code reviews on this repo. Configure [here](https://www.cursor.com/dashboard/bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
## Stack Context
Part 2 of a 3-PR stack moving memory deduplication into the SDKs. See `sdk-dedup/tools-ts` (parent) for the full context and the TypeScript implementation this mirrors.
## What?
Port the normalized, priority-ordered (`static > dynamic > search`) profile deduplication into the Python SDKs.
- Each request injects one **owned memory block that replaces** the prior block rather than accumulating.
- Dedup is **request-local** (no shared state), so it stays correct under concurrency.
Covers OpenAI, Agent Framework (middleware + context provider), Cartesia, and Pipecat.
## Why?
Keeps the Python SDKs at behavioral parity with the TypeScript SDK so all integrations deduplicate memory the same way.
## Testing
- OpenAI: 31 passed, 11 skipped (live)
- Agent Framework: 59 passed
- Cartesia: 8 passed
- Pipecat: 8 passed
🤖 Generated with [Claude Code](https://claude.com/claude-code)
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Medium Risk**
> Changes memory formatting and system-prompt injection across multiple SDK integrations; incorrect dedup or replacement could alter LLM context, but there is no auth or data-store risk.
>
> **Overview**
> Ports **normalized cross-source memory deduplication** and **replace-not-append injection** into the Python OpenAI, Agent Framework, Cartesia, and Pipecat packages so they match the TypeScript SDK behavior.
>
> **Deduplication** uses request-local keys: strip optional `[YYYY-MM-DD]` prefixes, normalize whitespace, and compare with `casefold`, with priority **static → dynamic → search**. In **`query` mode**, profile static/dynamic are excluded from dedup input so facts that only appear in search (or overlap profile) are not dropped before formatting.
>
> **Injection** no longer appends memory text every turn. OpenAI and Agent Framework middleware **strip prior owned `<supermemory context="user-memories" readonly>` blocks** and **replace** them once per request while keeping the caller’s system instructions; extra system messages lose stale blocks only. New helpers (`strip`/`replace`/`wrap`) live in each package’s utils.
>
> Tests cover normalized fact variants, query-mode search retention, and stale block replacement.
>
> <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit 42f308b224. Bugbot is set up for automated code reviews on this repo. Configure [here](https://www.cursor.com/dashboard/bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
## 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
- 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)
Google is not approving new authorizations while it re-reviews our app, so
every path that starts a new Google connection now shows a PAUSED badge and a
"Notify me" button instead of Connect.
- Existing connections are untouched: sync, file picking and history still work.
- Notify me fires a connector_paused_clicked PostHog event and remembers the
choice in localStorage, so we can pull who to email when the review clears.
- One list in lib/connector-availability.ts drives every surface; removing the
two entries turns Google back on.
- First-landing modal on the Company Brain home: book a 30-min setup call, or install Slack yourself. Dismissal stored in localStorage.
- Setup call also reachable from a header icon, the user menu, and the onboarding research rail.
- Drops the desktop Invite button from the header; invite stays in the stats row and mobile menu.
Cherry-picks two cleanup PRs and finishes the job. Net 262 deletions.
- #1473 (@abhay-codes07): drops a `console.log` in the fullscreen note editor that printed the whole note body on every keystroke, which PostHog session replay can capture.
- #1563 (@ishaanxgupta): removes `/api/onboarding/research` and `/api/onboarding/extract-content`. Neither has a caller anywhere in the repo, and both spent metered Exa and xAI quota. This reverts the guards added for them in #1589, which only existed to make unreachable code safe.
- On top: `EXA_API_KEY`, `XAI_API_KEY` and the `@ai-sdk/xai` dependency are removed, since deleting those routes left them with no consumer.
Co-Authored-By: abhay-codes07 <182421137+abhay-codes07@users.noreply.github.com>
Co-Authored-By: ishaanxgupta <124028055+ishaanxgupta@users.noreply.github.com>
Cherry-picks #1582, #1583, #1584 and #1585 from @Sravanjangam (security audit #1578) onto one branch.
- MCP: `get_document` scopes to the active space like its sibling read tools, `fetch-graph-data` bounds page/limit, `guided-save` caps prefill at 200k, and `whoAmI` no longer returns the transport session id.
- ai-sdk: search limit clamped to 1-50 with a 30s client timeout.
- validation: caps on `DocumentsWithMemoriesQuerySchema.limit` and `BulkDeleteMemoriesSchema.containerTags`.
- Raycast: `metadata.url` is parsed and only http(s) is offered to the OS opener.
Dropped his `add_memory` permission gate: it checked the target against the list of existing spaces, so writes to a new space failed and the no-active-space path surfaced `No write access to space "undefined"`. Write permission stays enforced in the API via `containerTagGate`.
Hardening and consistency rather than a security fix, since the API already enforces every permission boundary here.
Co-Authored-By: Sravanjangam <163002695+Sravanjangam@users.noreply.github.com>
Cherry-picks #1587 from @Sravanjangam, plus the OAuth half on top.
When the auth backend is slow or returns a 5xx, the MCP server currently answers `invalid_token`. That is the protocol's signal to discard the credential and re-authenticate, so a brief upstream blip logs every connected client out, and `sm_` API key users have no automatic way back. These requests now return 503 with `Retry-After: 5` so clients retry instead.
His change covered the API key path only. This shares one `transientAuthErrorFor` helper between `validateApiKey` and `validateOAuthToken`, so a JWKS timeout or a 5xx also returns 503 on the OAuth path that Claude, Cursor and browser clients use.
Genuinely bad tokens are unaffected: bad signature, expired, and no-matching-key still resolve to 401. Verified across all seven cases.
Co-Authored-By: Sravanjangam <163002695+Sravanjangam@users.noreply.github.com>
