Update tool descriptions, proactive search guidance, and v4 API examples
across SKILL.md and sdk-guide reference.
Co-authored-by: Cursor <cursoragent@cursor.com>
Use client.add and search.memories hybrid mode, improve profile memory
deduplication for string/pydantic items, and add dedupe unit tests.
Co-authored-by: Cursor <cursoragent@cursor.com>
Run pytest for openai-sdk-python, agent-framework, cartesia, and pipecat
packages on PRs touching those paths.
Co-authored-by: Cursor <cursoragent@cursor.com>
Adds one FAQ to the ChatGPT Web setup guide for making Supermemory the default memory.
- shows how to disable ChatGPT memory and optionally move the existing summary
- adds light and dark screenshots plus the custom instruction to paste
Tested with `mintlify validate` and `mintlify broken-links`.
### TL;DR
Documents the new `ids` parameter for the `forget-matching` endpoint, allowing exact memory deletion without semantic search.
### What changed?
The `forget-matching` endpoint now accepts either a `query` (semantic search-based forgetting) or an explicit `ids` list (direct deletion by memory ID) — one or the other must be provided. The docs have been updated to reflect this:
- The `query` parameter is now marked as `one of*` rather than required, and `ids` is introduced as an alternative with the same mutual-exclusivity constraint.
- `threshold` is clarified as applying to `query` mode only.
- Code examples for both JavaScript and cURL now show the recommended two-step pattern: run a `dryRun` with `query`, then apply using the `ids` returned from the preview — avoiding drift if the container changes between steps.
- A new `<Tip>` block explains why passing `ids` on the apply step produces a more deterministic delete than re-running the `query`.
### How to test?
1. Call `forget-matching` with `dryRun: true` and a `query` to retrieve candidate `id`s.
2. Re-call with `dryRun: false` and the `ids` from step 1 to confirm only those exact memories are forgotten.
3. Verify that passing `ids` belonging to a different `containerTag` are ignored.
4. Confirm that providing both `query` and `ids`, or neither, returns an appropriate validation error.
### Why make this change?
Re-running a `query` on the apply step can produce different results if the container was modified between the preview and the apply. Exposing `ids` as a first-class parameter lets callers pin the delete to exactly the set they reviewed, making bulk forgetting safer and more predictable.
Header-auth MCP servers like Plane need an API key plus a second header,
which the custom connector dialog had no way to collect.
- Restructured on the Claude connector pattern: name + URL up front,
credentials behind collapsed Advanced settings
- Adds API key, header name, and repeatable extra header rows
## What and why
Make skills created through Company Brain visible in the existing Settings catalog without a manual reload. The UI labels Slack-originated skills and refreshes the catalog while the Settings page is open.
```mermaid
flowchart LR
A[Slack approval] --> B[Company Brain skill catalog]
B --> C[Skills API query]
C --> D[Settings Skills list]
D --> E[Created by Company Brain label]
```
## Validation
- `bunx biome check apps/web/components/settings/company-brain-skills.tsx apps/web/components/settings/company-brain-skills/domain.ts apps/web/components/settings/company-brain-skills/skill-row.tsx apps/web/hooks/use-brain-skills.impl.ts` — passed
## Impact
Settings polling refreshes every 15 seconds and on window focus. It does not change the Nova/browser chat workflow or create skills from that surface.
Updates the Supermemory MCP docs for the revamped tool, space, widget, and OAuth flows.
- adds a screenshot-backed ChatGPT Web setup guide with light and dark variants
- refreshes the overview, setup, tools, spaces, and widget docs
- keeps manual JSON configuration in a dropdown
Tested all four local MCP docs routes and image references.
for mcp image light mode -> dark mode images and dark mode has light mode (since the background was blending in i made this way to refocus user attention on the screenshots)
Fixes cross-host graph rendering and moves widget uploads off the JSON/base64 tool transport.
- render graph data from the launcher result without a second tool call
- stream multipart uploads through one-time, short-lived upload sessions
- remove temporary widget diagnostics and redundant unit tests
Tested with Biome, TypeScript, 17 unit tests, a Wrangler deployment dry-run, and live graph rendering in ChatGPT and Claude. Authenticated E2E setup is currently blocked by the saved OAuth refresh session returning `invalid_grant: session not found`.
Keep docs asset URLs repo-root-relative and pass images as literal MDX children so Mintlify can compile them through OptimizedImage under the /docs mount.
Mintlify's official guidance says: “Image paths are root-relative from your docs repository.” It also says relative paths such as `./screenshot.png` are unsupported. See [Image embeds](https://www.mintlify.com/docs/create/image-embeds).
The existing `/images/...` paths were correct. The failure came from passing them through custom-component string props, which kept Mintlify from seeing those images during its MDX transform.
- fix hero, building-block, and Slack avatar images
- preserve Slack avatar clipping
- normalize Hermes and Company Brain icon sizing
Tested with Mintlify validation, broken-link checks, and browser checks across every changed route.
Fixes broken docs navigation and asset paths from the site audit.
- serves docs images from `/images` and adds the missing Cartesia icon
- corrects homepage, console, and LinkedIn destinations
- removes agent-only comparison headings from the web TOC
Tested with Mintlify validate and Mintlify broken-links.
- Header pill with trial days left (Autumn-first, org metadata fallback)
- Brain home: Your Company Brain timeline card (trial strip, milestones from /brain/overview) promoted to top-right
- Trial copy in CB onboarding Slack step and docked header
- Brain home now reads the new /brain/overview endpoint (drops the dead /brain/connections fetch)
Fixes ENG-1142
## Stack Context
This is the frontend half of the Company Brain Skills feature. The harness is implemented in supermemoryai/mono#2611.
## What?
Add Skills settings with separate Org-wide and Personal sections, Markdown upload autofill, scoped creation and editing, approval controls, and server-driven permissions.
## Why?
Members need a focused way to manage their private playbooks while admins create and approve organization-wide guidance.
## Related
- Harness: https://github.com/supermemoryai/mono/pull/2611
---
**Session Details**
- Session: [View Session](https://supermemory.us1.vorflux.com/agent-sessions/d8c77451-8f55-47ab-a182-5c98da616263)
- Requested by: Sreeram Sreedhar (sreeram@supermemory.com)
- Address comments on this PR. Add `(aside)` to your comment to have me ignore it.
Fixes MCP app submission metadata and makes widget delivery consistent across hosts.
- content-hash widget resources and set the production widget domain
- add typed structured outputs to direct tools and scope default-space calls
- keep graph rendering compatible with both initial results and app-side loading
Tested with `bun run check-types` and `bun run test:unit` (42 tests).
Adjusts login handling for a limited credential-validation flow. Normal Google and magic-link sign-ins are unchanged for other accounts.
Tested with direct login validation and a production build.
ChatGPT can omit nullable nested fields from structured tool results and does not reliably expose result metadata to MCP Apps. Keep graph data in `structuredContent`, tolerate missing document titles, and bundle React inside the widget so the graph renders consistently across hosts.
- use the deployable `app-v4` resource URI
- keep the graph response and widget schema aligned
- remove the `esm.sh` runtime dependency
Tested with typecheck, 42 unit tests, production widget build, 36 branch-local authenticated E2E tests, and a live ChatGPT graph render.
Moves MCP App results onto explicit runtime schemas so hosts can distinguish model-visible output from widget-only graph data.
- advertises output schemas for structured tools
- validates API, session, and widget boundaries instead of asserting response types
- marks additive app writes as non-destructive and removes redundant widget typing
Verified with MCP typecheck, 42 unit tests, and the production widget build. Claude Desktop host validation is in progress against a temporary tunnel.
Agent switcher snapped back to the just-connected plugin while the API-key banner was open; fixed the effect so manual tab clicks stick. Replaced the double header + blurred install-steps overlay with named chip tabs (matching existing chip style), inline Connect + Docs, and a plain step-title preview.
Fixes ENG-1141
Registers `SpaceState` before the stateless MCP starts routing requests through it. The class is intentionally unused here, so this changes no request behavior.
Rollout:
1. Apply this exact commit once with `wrangler deploy`, not `wrangler versions upload`.
2. Rerun the Workers check and merge this parent PR.
3. Land #1120, which adds the active-space methods and request routing.
Verified with the MCP widget build, isolated class typecheck, and Wrangler deploy/version dry runs.
Configure sections were local useState, so they could not be linked or bookmarked and always opened on the default section. Each section is now a route (/configure, /configure/models, /configure/workspace-prompt, /configure/proactivity, /configure/automations), mirroring the existing /integrations/[card] pattern. The shell renders from the segment layout so switching sections does not remount the app, and legacy /?view=configure links forward to /configure.
Fixes ENG-1140
Workspaces with hundreds of Slack channels made the plain select unusable, so the channel exception picker is now a Popover + Command combobox that filters as you type. The exceptions block is also reworked into one list card with an inline add row, matching the max-w-3xl measure used by the workspace prompt pane.
Fixes ENG-1138
Adds a dedicated Workspace Prompt editor for Company Brain organizations while preserving the existing Organization Context ingestion-filter controls for every organization manager.
## Changes
- Keeps Organization Context byte-for-byte unchanged and available independently to all organization managers.
- Adds Workspace Prompt as a separate Company-Brain-only section below it, using the established settings styling and contextual divider.
- Describes Workspace Prompt as persistent guidance that can shape operating preferences, priorities, source/tool choices, workflows, terminology, formatting, and communication style.
- Adds nullable, 1,500-character `workspacePrompt` support to shared request, GET response, and PATCH response contracts.
- Aligns PATCH validation with the real `{ orgId, orgSlug, updated }` API response.
- Merges canonical `updated` settings into the submitting organization’s cache, then exactly refetches that organization.
- Preserves drafts during background refetches, isolates organization switches, retains actionable errors, accessibility, empty `filterPrompt` compatibility, and `X-App-Source: nova`.
## Testing
- Passed focused Biome checks on all changed files.
- Passed `packages/lib` and `packages/validation` TypeScript checks.
- Verified GET/PATCH settings response contracts, partial/null/limit validation, canonical cache merge, and exact organization-bound invalidation.
- Verified Organization Context remains unchanged and Workspace Prompt is separately Company-Brain/manager-gated.
- Confirmed no remaining Workspace Persona identifiers.
- Public preview returns HTTP 200; authenticated settings interactions remain unavailable without a saved OAuth session.
- Full web type-check remains blocked by unrelated baseline diagnostics; none reference changed files.
- No dedicated tests were added, per requester instruction.
---
**Session Details**
- Session: [View Session](https://supermemory.us1.vorflux.com/agent-sessions/7544b72b-aeca-48e2-81c3-514df21cd081)
- Requested by: Soham Daga (soham@supermemory.com)
- Address comments on this PR. Add `(aside)` to your comment to have me ignore it.
## Summary
- Add custom assistant-message rendering for Nova connector tool results
- Show integration-style setup/status cards with icon, status pill, setup steps, docs links, copy buttons, and key reveal/generate action
- Keep plugin API keys client-side only by calling the existing `/v3/auth/key?client=...` endpoint from the UI
- Add Nova empty-state suggestions for Cursor setup and active plugins
## What changed
- Make `/brain` reuse the active Company Brain, switch to a single existing Company Brain, show a picker for multiple choices, or create one only when none exists.
- Wait for active-organization restoration before making that decision.
- Make Company Brain onboarding match organizations by the confirmed company domain and never offer unrelated-domain workspaces.
- Create a new Company Brain when no matching workspace exists and show an actionable workspace-limit toast when creation is blocked.
- Improve the organization picker, loading, and error states.
## Why
The previous flows could use or mutate the currently active normal organization, start research against stale Company Brain metadata, or offer unrelated Company Brain workspaces after a quota failure.
## Impact
Normal organizations are no longer silently converted. Research is scoped to the Company Brain for the confirmed domain, and users receive a clear recovery path when they reach their workspace limit.
This keeps the existing `{ domain }` research API contract; no organization-reconfiguration API is required.
## Validation
- Biome checks passed for all five changed web files
- Targeted web TypeScript diagnostics reported no errors for the changed files
- React Doctor against `origin/main`: no issues found
- `git diff --check`
No test files were added.
Adds a dismissible Company Brain card to the dashboard header slot and a permanent entry in the profile menu for users whose org has no company brain, both linking to team onboarding.
Onboarding now honours ?mode=team so a personal-domain email arriving from those CTAs isn't routed to personal onboarding.
Fixes ENG-1132
<!-- VORFLUX_AGENT_PR_BODY_BEGIN -->
Company Brain share snapshots now use the active organization’s branding instead of the signed-in user’s personal name.
## Changes
- Detect Company Brain workspaces through the canonical hook.
- Render the normalized organization name with `Company Brain`, preserving personal share branding for other workspaces.
- Handle missing, organization-suffixed, and already-possessive organization names.
## Testing
- **Passed:** `node_modules/.bin/biome ci apps/web/components/share-modal.tsx`
- **Passed:** `git diff --check -- apps/web/components/share-modal.tsx`
- **Baseline failure:** `node_modules/.bin/tsc --noEmit --incremental false -p apps/web/tsconfig.json` reports existing workspace diagnostics. The only diagnostic in `share-modal.tsx` is present on `HEAD`; none reference the new branding code.
- **Blocked:** authenticated visual verification was not performed because no authenticated browser state was available and no login retry was requested.
- Blocker screenshot:
- Blocked-flow recording:
---
**Attached Images and Videos**
🎥 [View recording: share-branding-walkthrough.webm](https://api.us1.vorflux.com/assets/artifacts/c3VwZXJtZW1vcnk6Zjo3NDI1.PLlwgZToeGPRdV49tEQESgrTiADIUq5pHQcQjzfGMQ0.mp4)
<!-- VORFLUX_AGENT_PR_BODY_END -->
---
**Session Details**
- Session: [View Session](https://supermemory.us1.vorflux.com/agent-sessions/22b72a15-9127-44be-b15b-3d341e26d016)
- Requested by: Dhravya Shah (dhravya@supermemory.com)
- Address comments on this PR. Add `(aside)` to your comment to have me ignore it.
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Low Risk**
> Copy-only UI in the share preview with no auth, API, or data-handling changes.
>
> **Overview**
> Share snapshot previews now switch branding when the workspace is **Company Brain**, instead of always showing the signed-in user’s name and **supermemory**.
>
> The modal uses `useHasCompanyBrain` and org data from auth to set the preview header: a normalized org possessive label (with fallbacks for missing names, trailing “organization”, and names that already end in `'s`) plus **Company Brain** as the product line. Non–Company Brain workspaces keep the existing personal **supermemory** branding.
>
> <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit 087019f357b8c9c028bd2e9e915a550bcce24573. Bugbot is set up for automated code reviews on this repo. Configure [here](https://www.cursor.com/dashboard/bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
## Stack Context
This is the Nova UI half of Slack account linking. The paired API and database work is [mono#2650](https://github.com/supermemoryai/mono/pull/2650).
## What?
- Preview the Slack and signed-in Supermemory identities before linking.
- Block accounts that are not already organization members.
- Require explicit confirmation when replacing an existing mapping.
- Handle account switching and invalid, expired, used, success, and retry states.
## Why?
Users whose Slack and Supermemory emails differ need a clear, secure way to confirm their identity. The page makes the identities and organization membership requirement explicit before creating or replacing a stable mapping.
Unscoped recall forced sm_project_default even when the caller could only read another organization space, causing a misleading 403 while list and graph operations succeeded. Let the search API choose the caller's readable scope, skip profile enrichment when no concrete scope is selected, and retain upstream error details.
Validated with Biome, Vite production build, and Wrangler deploy dry-run.
