Commit graph

1793 commits

Author SHA1 Message Date
Dhravya Shah
ec1817e8ca fix(docs): prefix raw internal href/src literals with /docs
index.mdx uses `mode: "custom"`, which renders raw HTML instead of
Mintlify's own components — Mintlify only auto-prefixes internal links
it generates itself (nav, Card href), not literal href/src strings in
raw <a>/<img> tags or JS string literals, so those still 404 under the
/docs mount. Fixed the homepage's raw <a href> links and the hardcoded
avatar path literals in the shared Slack-message snippet component.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-21 20:46:18 -07:00
Dhravya Shah
fa0823a300
fix(docs): prefix JSX-prop image paths with /docs to fix 404s (#1332)
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-21 20:27:44 -07:00
Dhravya Shah
f882f1104d
docs: restructure documentation site and update integration UI (#1331)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-07-21 20:19:30 -07:00
Dhravya Shah
816b85d756
fix(mcp): annotate tool safety hints for ChatGPT (#1330) 2026-07-21 14:45:45 -07:00
MaheshtheDev
9bbe436fab docs(brain): note trial attach after Slack OAuth (#1313)
## Summary
- Documents that mono attaches Scale 14d trial + Company Brain after Slack OAuth from `/brain`.

Stacks on #1310. Billing implementation is in mono.
2026-07-21 21:34:25 +00:00
MaheshtheDev
e39ba92cb4 feat(brain): add /brain Slack-first onboarding entry (#1310)
New /brain route creates the org straight from signup and redirects into the Slack install, so onboarding has no domain-confirmation step. Returning from OAuth shows an Open Slack handoff instead of a toast.

Also models the terminal research error state: polling stops, the UI retries once, and the docked header no longer gates Continue on research finishing.
2026-07-21 21:19:54 +00:00
Ishaan Gupta
2426305a2d
feat(extension): Add support across gemini & claude, live tool tip, auto complete support (#971)
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-07-21 13:12:20 -07:00
Rajarshi Datta
86c3ad69d1
fix(middleware): update deduplication logic for profile memories in query mode (#1243) 2026-07-21 19:25:32 +05:30
vorflux[bot]
566be20898
Update Gmail connector plan requirement docs (#1311)
Co-authored-by: Vorflux AI <249966464+vorflux[bot]@users.noreply.github.com>
2026-07-18 16:28:40 -07:00
sreedharsreeram
9824f0c9cd feat(web): configure Company Brain reasoning effort (#1307)
## Stack context

Stacks on #1306, which moves Company Brain settings into the revamped Configure page.

Backend contract and runtime support: supermemoryai/mono#2581. The UI safely hides any effort controls omitted by an older backend response.

## What changed

- Adds independent Low, Medium, High, and Extra high reasoning controls for Main, Triage, and Research.
- Saves model and reasoning edits together through the existing partial PATCH.
- Keeps controls visible but disabled for non-admin members.
- Explains that Extra high maps to High for Grok and GPT providers.

## Validation

- `bunx biome check apps/web/hooks/use-brain-models.ts apps/web/components/settings/company-brain-models.tsx`
- `bun run build` in `apps/web`
- `git diff --check`

The standalone web TypeScript command still reports pre-existing unrelated errors outside these files.

---
**Session Details**
- Session: [View Session](https://supermemory.us1.vorflux.com/agent-sessions/1c4f3ec7-a536-4105-bbe7-8b19e61f245f)
- Requested by: Sreeram Sreedhar (sreeram@supermemory.com)
- Address comments on this PR. Add `(aside)` to your comment to have me ignore it.
2026-07-18 19:12:45 +00:00
MaheshtheDev
20e585cd00 feat(web): revamp Company Brain configure page (#1306)
- New Configure tab with sidebar sections: Integrations, Models, Automations
- Merge org/personal connection tabs into one grid: per-card scope chips, admin scope dropdown, Slack as a card, custom MCP via modal
- Automations: always-visible template cards with dashed blank-create tile
- Home: Connect your tools only shows unconnected apps

Fixes ENG-1075
2026-07-18 18:45:03 +00:00
Abhay Singh
7c848a5da3
fix(web): declare entityContext in bulkLinkMutation so bulk link import works (#1260) 2026-07-18 19:15:59 +05:30
Paramveer singh
bec73e28ad
docs(tools): correct addMemory default in OpenAI middleware JSDoc (#1253) 2026-07-17 23:17:26 -07:00
Abhay Singh
86854efee6
fix(tools): make claude-memory file operations act on the exact file, literally (#1285)
Some checks failed
Publish Tools / publish (push) Has been cancelled
2026-07-17 18:24:09 +05:30
Abhay Singh
d8796277b0
fix(agent-framework): restore importability on current agent-framework-core releases (#1281) 2026-07-17 14:49:10 +05:30
Dhravya Shah
82c03a87ce
docs: drop Pro-plan banner for Claude Code & OpenCode (now free-tier) (#1298)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-16 19:38:08 -07:00
Dhravya Shah
400e2f4d7d
docs(readme): surface latest research numbers front and center (#1297)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-16 18:58:10 -07:00
ishaanxgupta
8d926332ab company brain responsiveness (#1239)
## Summary

- Improves the Company Brain header and stats cards on mobile without changing the desktop layout intent.
- Tightens the mobile Slack banner so the Slack logo is not duplicated and the card stays compact.
- Centers the onboarding step flow and card as one stack while keeping the logo independent.

before:
<img width="388" height="864" alt="image" src="https://github.com/user-attachments/assets/f02890e4-78d1-45cf-a819-97306df20d5c" />

after:
<img width="193" height="431" alt="image" src="https://github.com/user-attachments/assets/1b5d6907-1dc1-4d95-9b4f-2b40defecda5" />
<img width="391" height="865" alt="image" src="https://github.com/user-attachments/assets/67fb6009-bace-4c78-9b72-b4dfcdd79b90" />
<img width="385" height="865" alt="image" src="https://github.com/user-attachments/assets/f3c3d785-762e-49c2-92bb-461358eda418" />
<img width="394" height="865" alt="image" src="https://github.com/user-attachments/assets/f5943779-a141-467d-a350-80678f3a2513" />
2026-07-16 01:57:51 +00:00
MaheshtheDev
ef0026a23c feat(brain): Company Brain Models settings tab (#1292)
Adds an admin-gated Models tab (main/triage/research pickers) that reads/writes the mono /brain/models endpoint, shown only for Company Brain orgs. Extracts a shared useOrgMemberRole hook so the brain settings sections dedupe the getActiveMember call.

Fixes ENG-1054
2026-07-14 18:56:01 +00:00
Gautam Sharma
2cebe81512
fix(web): bypass auth proxy for local dev (#1213)
Co-authored-by: Dhravya Shah <dhravya@supermemory.com>
Co-authored-by: Dhravya Shah <dhravyashah@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 20:11:48 -07:00
Gautam Sharma
19d7f122b2
fix(web): use backend URL fallback for direct fetches (#1212)
Co-authored-by: Dhravya Shah <dhravyashah@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 20:02:24 -07:00
Haroon
e5e4e498f2
fix(tools): coerce limit/offset in ai-sdk schemas (#1202)
Co-authored-by: Dhravya Shah <dhravyashah@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 19:42:15 -07:00
Dhravya Shah
5567e82377
docs(self-hosting): configurable embeddings for Supermemory local (#1210)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-07-10 19:15:46 -07:00
Mrityunjay Raj
453185abf3
ci: add concurrency groups to workflows (#1221)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-10 19:15:32 -07:00
Gautam Sharma
6763c36d61
fix(extension): scope related memory search (#1215) 2026-07-10 19:15:29 -07:00
Gautam Sharma
bc6eb73d43
fix(tools): reject conflicting container config (#1214) 2026-07-10 19:15:25 -07:00
Bharath
09e3b78fc2
perf(lib): hoist customAlphabet factory in generateId (#1204) 2026-07-10 19:15:21 -07:00
Haroon
d77b6eb6d9
feat(memory-graph): configurable labels + popover z-index (#1201) 2026-07-10 19:15:17 -07:00
Abhay Singh
9487a928f6
feat(mcp): add listMemories tool for enumerating stored memories (#1183) 2026-07-10 19:15:12 -07:00
Abhay Singh
b49903a493
fix(web): make the finished-processing refresh effect actually fire (#1188) 2026-07-10 19:15:02 -07:00
Abhay Singh
72ab99a77b
fix(web): stop extractUrls treating email addresses as URLs (#1187) 2026-07-10 19:14:57 -07:00
Abhay Singh
95fc201072
fix(web): stop truncating multi-line plugin transcript messages (#1185) 2026-07-10 19:14:53 -07:00
pawan
942f03eef9
fix(cartesia-sdk): treat empty profile as no memories, not a retrieval error (#1164) 2026-07-10 19:14:49 -07:00
Dhravya Shah
36b07e2a26
chore(tools): bump @supermemory/tools to 2.1.0 (#1234)
Some checks failed
Publish Tools / publish (push) Has been cancelled
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 18:55:15 -07:00
Sandipan kundu
2163f592b7
fix(tools,validation): persist tool-call turns in conversation memory & tidy search thresholds (#1211)
Co-authored-by: Dhravya Shah <dhravyashah@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 18:54:56 -07:00
Abhay Singh
501613b6bc
fix(tools): repair SDK call mismatches that broke five tools (#1186) 2026-07-10 18:30:41 -07:00
Sepuri Sai Krishna
67b6585346
fix(web): block IPv6 literals in OG scraper SSRF guard (#1154) 2026-07-10 18:20:43 -07:00
Abhay Singh
c00f3e1b22
fix(web): match YouTube URLs by hostname instead of substring (#1182) 2026-07-10 16:20:18 -07:00
Mrityunjay Raj
59a0147296
ci: add timeout-minutes to all workflow jobs (#1223) 2026-07-10 15:48:24 -07:00
Mrityunjay Raj
7785420eb0
ci: skip Claude review on fork PRs (#1231)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-10 15:46:25 -07:00
Mrityunjay Raj
398737fadc
ci: pass workflow_run id to github-script via env (#1227) 2026-07-10 15:22:23 -07:00
Mrityunjay Raj
f994180022
ci: gate @claude workflow triggers by author association (#1229)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-10 15:10:29 -07:00
MaheshtheDev
97888ce859 feat(web): Company Brain proactiveness (automations) settings (#1207)
Adds the **Proactiveness** settings tab for Company Brain channel/DM automations.

- Accordion list of automations — collapsed rows with an instant enable toggle + **Run now**, expand to edit.
- Two-column editor: prompt (left) / deliver-to channel or DM, frequency, day, time (right), with local-timezone-aware cron.
- Preset gallery (connection-first, category-diverse) for empty state + a New-automation menu.
- DM delivery option with a tooltip explaining channel visibility + personal-connection fallback.
- Profile-menu entry (gated on Company Brain).

Pairs with the API automations work: **supermemoryai/mono#2480**.
2026-07-07 21:20:50 +00:00
MaheshtheDev
af61880da1 feat(web): add staff custom MCP connection cards (#1199)
---
**Session Details**
- Session: [View Session](https://supermemory.us1.vorflux.com/agent-sessions/cd042b68-db46-431f-982c-3070096a37bd)
- Requested by: Unknown
- Address comments on this PR. Add `(aside)` to your comment to have me ignore it.
2026-07-06 06:11:09 +00:00
MaheshtheDev
d7050ed332 feat(web): company brain onboarding research UI (#1197)
- Confirm-domain step, then live research transcript + action rail
- Poll research status; client-side force-start fallback

---
**Session Details**
- Session: [View Session](https://supermemory.us1.vorflux.com/agent-sessions/4f4c1321-9b65-4dac-9906-8b78c4c32926)
- Requested by: Unknown
- Address comments on this PR. Add `(aside)` to your comment to have me ignore it.
2026-07-05 00:06:02 +00:00
sohamd22
8c35c1ecad review suggestions option for inferred memories (#1138)
### TL;DR

Adds a swipeable "Review suggestions" card to the dashboard that lets users approve or decline inferred memories surfaced by Nova.

### What changed?

- Added a `ReviewMemoriesCard` component that appears in the "Suggested for you" section of the dashboard (both desktop and mobile layouts). The card is hidden when there are no pending inferred memories, so it never renders empty chrome. While the modal is open, the displayed count is frozen so the trigger button doesn't tick down or disappear mid-session. Switching spaces closes the modal automatically.
- Added a `ReviewMemoriesModal` component that presents inferred memories as a swipeable card deck. Users can approve (swipe right / ✓), decline (swipe left / ✗), or skip each memory. The modal includes:
  - Drag-to-swipe with a full-card color wash (green for keep, red for decline) and verdict pills that intensify as the swipe threshold approaches
  - Keyboard support: `→` to approve, `←` to decline, `↓` or `Space` to skip, and `Cmd/Ctrl+Z` to undo
  - An undo button that steps back one card and reverts the server-side decision, using refs to avoid stale-state bugs during rapid interactions
  - A progress dot indicator showing position in the queue alongside a numeric counter
  - A "All caught up" completion state summarising how many memories were kept
  - Reduced-motion support via `useReducedMotion`
  - The card queue is snapshotted when the modal opens so cache updates from review mutations don't reshuffle the stack mid-session
- Added a `useInferredMemories` hook to fetch the pending review queue for a given container tag, and a `useReviewInferredMemory` mutation hook that calls the review endpoint. On success it removes the reviewed entry from the cached queue directly; on undo it invalidates the query to refetch the restored memory from the server.
- Registered two new API schema entries: `GET /container-tags/:containerTag/inferred` to fetch the pending queue and `POST /container-tags/:containerTag/inferred/:memoryId/review` to submit an approve, decline, or undo action.

### How to test?

1. Ensure there are inferred memories pending review for a container tag.
2. Open the dashboard — a "Review suggestions" card should appear in the "Suggested for you" section showing the count of pending memories.
3. Click the card to open the modal and swipe or use the buttons/keyboard to approve, decline, or skip memories.
4. Verify that approved and declined memories are removed from the queue after each decision and that the completion state appears once all cards are reviewed.
5. Use the undo button or `Cmd/Ctrl+Z` to step back through decisions and confirm the server-side state is reverted correctly.
6. Confirm the card does not render when there are zero pending inferred memories.
7. Switch spaces while the modal is open and confirm it closes without carrying state into the new space.

### Why make this change?

Nova infers memories on behalf of users but may not always be fully confident in them. This feature gives users a lightweight, low-friction way to review and curate those suggestions directly from the dashboard, improving the quality and trustworthiness of their memory store.
2026-07-04 20:57:33 +00:00
MaheshtheDev
acd2fea9a9 feat(web): hide getting-started once setup done, swap setup tile (#1190)
Hide the Getting Started checklist when all 3 onboarding steps complete, letting Recent memories go full-width. Swap the Setup 3/3 stat tile to a live Last updated timestamp once setup is done.

---
**Session Details**
- Session: [View Session](https://supermemory.us1.vorflux.com/agent-sessions/afbb6d10-e42e-4b40-aac9-90aba9532ec7)
- Requested by: Unknown
- Address comments on this PR. Add `(aside)` to your comment to have me ignore it.
2026-07-03 04:12:38 +00:00
MaheshtheDev
d4c451c3ce feat(web): brain connections board + MCP connect from web (#1181)
Connections board on brain home: featured app tiles with OAuth/static connect against brain/mcp-connections, agent preview prompts, connector icon set, and reworked company-brain connections in settings.

---
**Session Details**
- Session: [View Session](https://supermemory.us1.vorflux.com/agent-sessions/e37671c7-3893-48d6-ad66-73200826c04d)
- Requested by: Unknown
- Address comments on this PR. Add `(aside)` to your comment to have me ignore it.
2026-07-02 16:24:50 +00:00
MaheshtheDev
42f3aec885 feat(web): company brain onboarding redesign + connector entitlement (#1178)
- onboarding: unified About step, mode-aware Sources, Slack-focused Flows step, connect feedback (toast + connected state), auto-draft company description from domain
- brain-home: Active members stat + invite, real OneDrive icon
- useConnectorAccess hook so company_brain unlocks pro-tier connectors across onboarding + integrations
- fix company-brain-connections crash on empty connections

---
**Session Details**
- Session: [View Session](https://supermemory.us1.vorflux.com/agent-sessions/64a15b29-0848-42d1-af4c-138c5a27136f)
- Requested by: Unknown
- Address comments on this PR. Add `(aside)` to your comment to have me ignore it.
2026-06-30 22:01:20 +00:00
Dhravya Shah
e706a13877
Merge timeout additions for supermemory-mcp (#1144)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Polylane Automation <automation@nominal.ai>
2026-06-29 12:28:14 -07:00