This PR was opened by the [Changesets
release](https://github.com/changesets/action) GitHub action. When
you're ready to do a release, you can merge this and the packages will
be published to npm automatically. If you're not ready to do a release
yet, that's fine, whenever you add more changesets to main, this PR will
be updated.
# Releases
## @chat-adapter/discord@4.34.0
### Minor Changes
- 0fdb902: Add opt-in Discord Components v2 rendering for Chat SDK cards
via `contentFormat: DiscordContentFormat.ComponentsV2`.
- 5341f90: Ignore `@everyone`/`@here` pings by default in gateway mode.
Previously the legacy gateway listener treated global pings as bot
mentions, so the bot responded to announcements. A new
`respondToGlobalMentions` config option (default `false`) restores the
old behavior when enabled, and also lets forwarded gateway messages opt
in via the `mention_everyone` field.
- 6c2a391: Add support for renaming native Discord thread channels.
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/slack@4.34.0
### Minor Changes
- 1721fa0: Add support for Slack's Agent messaging experience
(`agent_view`).
- New core event `onAppContextChanged` with a normalized
`AppContextEntity[]` describing the user's active view (channel / canvas
/ list / message / unknown).
- `AppHomeOpenedEvent` now carries the folded active-view context as
`entities` and the opened `tab` (Slack: `"home"` / `"messages"`), so
handlers can tell a Home-tab open from the DM-open signal under
`agent_view`.
- Slack adapter: new `agentView` config flag (under `agent_view`,
`app_home_opened` is the DM-open signal regardless of tab and folded
context is surfaced), routing for the `app_context_changed` event, and a
`getAppContext(message)` helper to read the folded context on DM
messages.
- `setSuggestedPrompts` now accepts an optional thread reference
(agent_view lets prompts sit at the top of the agent conversation).
- Under `agentView`, DM (Messages-tab) messages are threaded per new
Slack's model — each user message is a thread root (`thread_ts ?? ts`).
Conversation-scoped threads returned by `openDM()` keep working: when
that thread is subscribed, incoming top-level DM messages route to it.
- `createSlackAdapter` env auth fallback (`SLACK_BOT_TOKEN` /
`SLACK_CLIENT_ID` / `SLACK_CLIENT_SECRET`) is now disabled only when an
auth or verification field (`botToken`, `clientId`, `clientSecret`,
`installationProvider`, `signingSecret`, `webhookVerifier`) is passed
explicitly, instead of by any config object — so `createSlackAdapter({
agentView: true })` still picks up env credentials, while
explicit-secret configs stay immune to ambient env vars.
- Bumped `@slack/web-api` to `^7.18.0` (adds the optional `thread_ts`
typing for `setSuggestedPrompts`).
- 4717a38: Add chart support and richer table rendering, with native
Slack data table and data visualization blocks.
- New core `ChartElement` and `Chart()` builder (JSX supported) with
pie, bar, area, and line charts, mirroring Slack's data visualization
model: pie charts take `segments`, series charts take named `series`
plotted against shared `categories` with optional `xLabel`/`yLabel`.
- `TableElement` / `Table()` gain optional `caption` (accessible table
description) and `pageSize` (rows per page) fields.
- Charts degrade gracefully on platforms without native chart support:
the underlying data renders as a text table via the shared card fallback
(new `chartElementToFallbackText` helper).
- Slack adapter: card tables now render as [data table
blocks](https://docs.slack.dev/reference/block-kit/blocks/data-table-block)
by default — paginated and sortable — instead of plain table blocks.
Header-only tables keep the plain table block; tables exceeding Slack
limits (100 data rows, 20 columns, 10,000 characters) fall back to ASCII
as before.
- Slack adapter: card charts render as [data visualization
blocks](https://docs.slack.dev/reference/block-kit/blocks/data-visualization-block).
Charts violating Slack constraints (50-character title, 12
segments/series, 20 categories, 20-character labels, one data point per
category, max 2 charts per message) fall back to a text rendering
instead of being rejected by the API.
- The `@chat-adapter/slack/blocks` subpath gets the same treatment:
`SlackChartElement` types, `chart` card children, data table rendering,
and matching limits.
- `postMessage` now surfaces Slack's per-block validation details when
the API rejects blocks (`invalid_blocks`), instead of the bare "An API
error occurred" message.
- 0f743c9: Add declarative agent-experience config and harden native
streaming:
- `suggestedPrompts` — a static payload or per-thread resolver, applied
automatically when an assistant/agent thread opens
(`assistant_thread_started` in legacy `assistant_view`, or a
Messages-tab `app_home_opened` under `agentView`, where prompts pin at
the top of the agent conversation without a `thread_ts`). The resolver
receives the thread context (`channelId`, `userId`, legacy
`threadTs`/`teamId`/`enterpriseId`, and active-view `entities` under
`agentView`); returning `null`/`undefined` skips the thread. Prompts
beyond Slack's 4-prompt limit are dropped with a warning, and
resolver/API failures are logged without failing the webhook.
- `loadingMessages` — default rotating status strings for the assistant
thinking indicator, used by `startTyping` and `setAssistantStatus` when
no explicit status/messages are passed.
- `nativeStreaming` config (default `true`). Set `false` on Slack
flavours without the `chat.startStream` family (e.g. GovSlack) to always
stream via post-and-edit.
- If the workspace rejects the first native streaming call, `stream()`
now falls back to throttled post-and-edit mid-stream instead of failing
the reply; already-consumed text is preserved. Permanent platform errors
(`unknown_method`, `method_deprecated`, `feature_not_enabled`) latch
native streaming off for subsequent streams on the adapter instance.
Structured chunks (`task_update` / `plan_update`) are skipped in
fallback mode.
- `feedbackButtons` — append Slack's native thumbs up/down
(`context_actions` + `feedback_buttons` block) to every streamed reply.
Pass `true` for defaults or an options object (`actionId`, labels,
values); clicks dispatch through `bot.onAction` with a positive/negative
value. A `buildFeedbackButtonsBlock(options?)` helper is exported for
attaching the block to non-streamed messages.
New exported types: `SlackFeedbackButtonsOptions`,
`SlackSuggestedPrompt`, `SlackSuggestedPrompts`,
`SlackSuggestedPromptsContext`, `SlackSuggestedPromptsOptions`.
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/telegram@4.34.0
### Minor Changes
- 8d7ccdb: Add Telegram media group uploads for multiple files and
attachments.
### Patch Changes
- 2531a42: Fix `detectMention` (and the Telegram adapter's
`isBotMentioned`) falsely matching `@bot` when `@bot-dev` is mentioned.
`\b` (word boundary) matches between a word character and a hyphen, so
`/@bot\b/` incorrectly matches `@bot-dev`. Replaced with `(?![\w-])` to
exclude hyphens.
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/web@4.34.0
### Minor Changes
- 6714efc: Support AI SDK v7 as a peer dependency.
- `chat` now accepts `ai@^6.0.182 || ^7.0.0` (`chat/ai` tools work with
both majors).
- `@chat-adapter/web` now accepts `ai@^6 || ^7`, `@ai-sdk/react@^3 ||
^4`, `@ai-sdk/svelte@^4 || ^5`, and `@ai-sdk/vue@^3 || ^4`.
- The `chat/ai` tool factories now declare explicit `Tool<Input,
Output>` return types instead of relying on inference, so the published
declarations no longer depend on `ai` internals that changed in v7. The
public type surface is unchanged.
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/whatsapp@4.34.0
### Minor Changes
- 2338a66: Add `sendTemplate()` for sending pre-approved template
messages, enabling business-initiated conversations outside the 24-hour
customer service window
- 8bd8a57: Implement outbound file and attachment sending for the
WhatsApp adapter.
Supports binary `FileUpload` uploads, typed `Attachment` payloads
(binary or HTTPS link passthrough), multi-file sequential sends, smart
MIME-to-message-type mapping, caption placement with audio/long-text
fallbacks, and card+file sequencing.
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/x@4.34.0
### Minor Changes
- 4bca64f: add image upload support to X posts and DMs via the chunked
media upload endpoints
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## chat@4.34.0
### Minor Changes
- 1721fa0: Add support for Slack's Agent messaging experience
(`agent_view`).
- New core event `onAppContextChanged` with a normalized
`AppContextEntity[]` describing the user's active view (channel / canvas
/ list / message / unknown).
- `AppHomeOpenedEvent` now carries the folded active-view context as
`entities` and the opened `tab` (Slack: `"home"` / `"messages"`), so
handlers can tell a Home-tab open from the DM-open signal under
`agent_view`.
- Slack adapter: new `agentView` config flag (under `agent_view`,
`app_home_opened` is the DM-open signal regardless of tab and folded
context is surfaced), routing for the `app_context_changed` event, and a
`getAppContext(message)` helper to read the folded context on DM
messages.
- `setSuggestedPrompts` now accepts an optional thread reference
(agent_view lets prompts sit at the top of the agent conversation).
- Under `agentView`, DM (Messages-tab) messages are threaded per new
Slack's model — each user message is a thread root (`thread_ts ?? ts`).
Conversation-scoped threads returned by `openDM()` keep working: when
that thread is subscribed, incoming top-level DM messages route to it.
- `createSlackAdapter` env auth fallback (`SLACK_BOT_TOKEN` /
`SLACK_CLIENT_ID` / `SLACK_CLIENT_SECRET`) is now disabled only when an
auth or verification field (`botToken`, `clientId`, `clientSecret`,
`installationProvider`, `signingSecret`, `webhookVerifier`) is passed
explicitly, instead of by any config object — so `createSlackAdapter({
agentView: true })` still picks up env credentials, while
explicit-secret configs stay immune to ambient env vars.
- Bumped `@slack/web-api` to `^7.18.0` (adds the optional `thread_ts`
typing for `setSuggestedPrompts`).
- 4717a38: Add chart support and richer table rendering, with native
Slack data table and data visualization blocks.
- New core `ChartElement` and `Chart()` builder (JSX supported) with
pie, bar, area, and line charts, mirroring Slack's data visualization
model: pie charts take `segments`, series charts take named `series`
plotted against shared `categories` with optional `xLabel`/`yLabel`.
- `TableElement` / `Table()` gain optional `caption` (accessible table
description) and `pageSize` (rows per page) fields.
- Charts degrade gracefully on platforms without native chart support:
the underlying data renders as a text table via the shared card fallback
(new `chartElementToFallbackText` helper).
- Slack adapter: card tables now render as [data table
blocks](https://docs.slack.dev/reference/block-kit/blocks/data-table-block)
by default — paginated and sortable — instead of plain table blocks.
Header-only tables keep the plain table block; tables exceeding Slack
limits (100 data rows, 20 columns, 10,000 characters) fall back to ASCII
as before.
- Slack adapter: card charts render as [data visualization
blocks](https://docs.slack.dev/reference/block-kit/blocks/data-visualization-block).
Charts violating Slack constraints (50-character title, 12
segments/series, 20 categories, 20-character labels, one data point per
category, max 2 charts per message) fall back to a text rendering
instead of being rejected by the API.
- The `@chat-adapter/slack/blocks` subpath gets the same treatment:
`SlackChartElement` types, `chart` card children, data table rendering,
and matching limits.
- `postMessage` now surfaces Slack's per-block validation details when
the API rejects blocks (`invalid_blocks`), instead of the bare "An API
error occurred" message.
- 6714efc: Support AI SDK v7 as a peer dependency.
- `chat` now accepts `ai@^6.0.182 || ^7.0.0` (`chat/ai` tools work with
both majors).
- `@chat-adapter/web` now accepts `ai@^6 || ^7`, `@ai-sdk/react@^3 ||
^4`, `@ai-sdk/svelte@^4 || ^5`, and `@ai-sdk/vue@^3 || ^4`.
- The `chat/ai` tool factories now declare explicit `Tool<Input,
Output>` return types instead of relying on inference, so the published
declarations no longer depend on `ai` internals that changed in v7. The
public type surface is unchanged.
### Patch Changes
- 5c926f1: Preserve markdown structural whitespace when extracting
normalized message text.
- 2531a42: Fix `detectMention` (and the Telegram adapter's
`isBotMentioned`) falsely matching `@bot` when `@bot-dev` is mentioned.
`\b` (word boundary) matches between a word character and a hyphen, so
`/@bot\b/` incorrectly matches `@bot-dev`. Replaced with `(?![\w-])` to
exclude hyphens.
## @chat-adapter/gchat@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/github@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/linear@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/messenger@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/shared@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
## @chat-adapter/teams@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/twilio@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
- @chat-adapter/shared@4.34.0
## @chat-adapter/state-ioredis@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
## @chat-adapter/state-memory@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
## @chat-adapter/state-pg@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
## @chat-adapter/state-redis@4.34.0
### Patch Changes
- Updated dependencies [5c926f1]
- Updated dependencies [2531a42]
- Updated dependencies [1721fa0]
- Updated dependencies [4717a38]
- Updated dependencies [6714efc]
- chat@4.34.0
## @chat-adapter/tests@4.34.0
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
## Problem
When I mention a Chat SDK-powered bot on GitHub like this:
```
@bot
hi there!
```
The mention doesn't trigger any handling, because the `mdastToString`
helper replaces all newlines with an empty string, so the logs look like
this:
```
[chat-sdk] Checking message patterns { patternCount: 0, patterns: [], messageText: '@bothi there' }
[chat-sdk] No handlers matched message {
threadId: 'github:RSO/chat:issue:29',
text: '@bothi there'
}
```
## Summary
- Preserve structural markdown whitespace when extracting normalized
plain text from mdast.
- Add regression coverage for newline-separated bot mentions in core
markdown extraction, GitHub issue/review comments, and Chat mention
routing.
- Add a patch changeset for the behavior fix.
## Testing
- `pnpm check`
- `pnpm knip`
- `pnpm test:workspace`
- `pnpm --filter chat test`
- `pnpm --filter @chat-adapter/github test`
- `pnpm --filter chat typecheck`
- `pnpm --filter @chat-adapter/github typecheck`
## Notes
- `pnpm validate` was attempted and reached the full Turbo test graph,
but failed on `packages/integration-tests/src/replay-discord.test.ts`
(`should skip bot's own messages in subscribed threads`). Rerunning
`pnpm --filter @chat-adapter/integration-tests test --
src/replay-discord.test.ts` passed, so this appears unrelated to the
markdown whitespace change.
- `.github/CONTRIBUTING.md` requires signed commits. This environment
has no `gpg` binary and no SSH signing identities loaded, so the commit
in this PR is currently unsigned and may need to be re-signed before
merge.
---------
Signed-off-by: dancer <josh@afterima.ge>
Co-authored-by: dancer <josh@afterima.ge>
Closes#690
## What
Widens the AI SDK peer dependency ranges so the Chat SDK installs
cleanly next to `ai@7`:
- `chat`: `ai@^6.0.182 || ^7.0.0`
- `@chat-adapter/web`: `ai@^6 || ^7`, `@ai-sdk/react@^3 || ^4`,
`@ai-sdk/svelte@^4 || ^5`, `@ai-sdk/vue@^3 || ^4`
This also unbreaks `create-chat-sdk` scaffolds, which install
`ai@latest` (now v7) next to `chat` and currently hit a peer conflict
out of the box.
## The one real v6 → v7 break
In v7, `tool()` with an `execute` function returns
`ExecutableTool<Tool<...>>` — an internal type from
`@ai-sdk/provider-utils` that `ai` does not re-export. The `chat/ai`
tool factories relied on inference, so declaration emit failed with
TS2742 (17 errors). The factories now declare explicit `Tool<Input,
Output>` return types, which is exactly the shape the previously
published `.d.ts` already had — the public type surface is unchanged,
and the emitted declarations only reference types from `ai` (portable
for consumers on either major).
Everything else checked out compatible:
- v7 stream parts keep `text-delta` / `finish-step` shapes, so
`fromFullStream` duck-typing works unchanged; `fullStream` remains as a
deprecated alias
- tool-level `needsApproval` is deprecated in v7 but still typed and
honored
- `createUIMessageStream`, `createUIMessageStreamResponse`,
`isTextUIPart`, `UIMessage`, `UIMessageStreamWriter`, `ChatInit`,
`DefaultChatTransport` all still exported — `@chat-adapter/web` needed
zero source changes
## Other changes
- devDependencies move to v7 so the workspace develops/tests against the
latest major
- `examples/nextjs-chat` and `examples/nuxt-chat` move to `ai@^7`
(required — mixing majors across the workspace fails typecheck, since
`chat`'s d.ts resolves `ai` types from its own devDependency)
- Test-only: the `ToolExecutionOptions` stub type is now derived from
`Tool["execute"]` because v7 made the generic parameter required
- Changeset included (minor for `chat` and `@chat-adapter/web`)
## Verification
The same source was verified against **both majors** (`ai@6.0.182` and
`ai@7.0.17`): `tsc --noEmit` and the full test suites (`chat`: 1035
tests, `@chat-adapter/web`: 21 tests) pass on each. `pnpm validate`
(knip + check + typecheck + test + build, including both examples) is
green on v7.
Note for adopters: `ai@7` itself requires Node.js ≥ 22 and is ESM-only;
`chat` keeps `engines.node >= 20` since `ai` is an optional peer.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Signed-off-by: chentsulin <chentsulin@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: dancer <josh@afterima.ge>
## Summary
<!-- What does this PR do? -->
Fix `detectMention` falsely matching `@bot` when `@bot-dev` is
mentioned. `\b` (word boundary) matches between a word character and a
hyphen, so `/@bot\b/` incorrectly matches `@bot-dev`. Replaced with
`(?![\w-])` to exclude hyphens.
## Test plan
<!-- How did you verify the changes? -->
## Checklist
- [x] All commits are signed and verified
- [x] `pnpm validate` passes
- [x] Changeset added (or N/A — see
[CONTRIBUTING.md](./CONTRIBUTING.md))
- [x] Documentation updated (or N/A)
---------
Signed-off-by: sivchari <shibuuuu5@gmail.com>
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
Adds support for Slack's [data
table](https://docs.slack.dev/reference/block-kit/blocks/data-table-block)
and [data
visualization](https://docs.slack.dev/reference/block-kit/blocks/data-visualization-block)
Block Kit blocks.
- **`chat`**: new cross-platform `ChartElement` + `Chart()` builder (JSX
supported) mirroring Slack's model — pie `segments`, or bar/area/line
`series` against shared `categories`. `Table()` gains optional `caption`
and `pageSize`. Charts degrade to a text table on other platforms via
the shared card fallback (`chartElementToFallbackText`).
- **`@chat-adapter/slack`**: card tables now render as paginated,
sortable `data_table` blocks by default (header-only tables keep the
plain `table` block; oversized tables still fall back to ASCII). Charts
render as `data_visualization` blocks; charts violating Slack
constraints — including the undocumented **max 2 charts per message** —
fall back to a text rendering instead of an API rejection. Same
treatment in the `@chat-adapter/slack/blocks` subpath.
- **`postMessage`** now surfaces Slack's per-block validation messages
on `invalid_blocks` errors (this is how the 2-chart limit was found).
- Example app gets a **Show Charts** button and table pagination on
**Show Table**; docs, feature matrices, and changeset updated.
Verified live against Slack: data table pagination/sorting and both
chart types render natively.
<table>
<tr>
<th>Data Table</th>
<th>Data Charts</th>
</tr>
<tr>
<td><img width="979" height="896" alt="CleanShot 2026-07-12 at 23 28 32"
src="https://github.com/user-attachments/assets/3307bd90-9322-452f-86fb-07d46446822d"
/></td>
<td><img width="955" height="879" alt="CleanShot 2026-07-12 at 23 29 02"
src="https://github.com/user-attachments/assets/ddb31a1b-e3fd-457c-a2e6-bde4934afebe"
/></td>
</tr>
</table>
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
## Summary
Add support for Slack's Agent messaging experience (`agent_view`), the
2026 replacement for `assistant_view`.
## Core (`chat`)
- New `onAppContextChanged` event carrying the active-view context as a
normalized `AppContextEntity[]` (`channel` / `canvas` / `list` /
`message` / `unknown`) describing what the user is currently viewing.
- `AppHomeOpenedEvent` now carries:
- the same folded active-view context as optional `entities`
- the opened `tab` (`"home"` / `"messages"`), so handlers can
distinguish a Home-tab open from the DM-open signal under `agent_view`
## Slack adapter (`@chat-adapter/slack`)
- **`agentView` config flag.** Under `agent_view`:
- `app_home_opened` is the DM-open signal and fires regardless of tab
(branch on `event.tab` if you also publish a Home view)
- DM messages are threaded per Slack's new model — each user message is
a thread root (`thread_ts ?? ts`)
- conversation-scoped threads returned by `openDM()` keep working: when
that thread is subscribed, incoming top-level DM messages route to it,
so `onSubscribedMessage` and per-thread state behave the same as in
legacy mode
- **`app_context_changed` routing** with normalized entities. Malformed
payloads degrade gracefully: a missing `context` yields `entities: []`,
and entities with a null/malformed `value` normalize to `kind:
"unknown"` — never a webhook 500.
- **`getAppContext(message)`** helper to read the folded active-view
context off a DM message.
- **`setSuggestedPrompts`** accepts an optional thread reference
(`agent_view` lets prompts sit at the top of the agent conversation).
- **Env auth fallback now keys off auth fields**: `SLACK_BOT_TOKEN` /
`SLACK_CLIENT_ID` / `SLACK_CLIENT_SECRET` fallback is disabled only when
an auth-related field (`botToken`, `clientId`, `clientSecret`,
`installationProvider`) is passed explicitly, rather than by the
presence of any config object. This lets non-auth options compose with
env auth — e.g. `createSlackAdapter({ agentView: true })` picks up env
credentials — and matches the semantics documented in the adapter's
AGENTS.md. *(Behavior change for callers passing non-auth-only configs
while relying on env vars being ignored.)*
- Bumped `@slack/web-api` to `^7.18.0` (adds the optional `thread_ts`
typing for `setSuggestedPrompts`).
## Docs
- New "Agent messaging experience" section on the Slack adapter page
(config, manifest snippet, threading model, openDM bridge).
- "Handling active-view context" section in handling-events, plus
`tab`/`entities` rows on the app-home event table.
- Callout: under `agent_view`, bot replies are threaded per user
message, so `conversations.history` only returns the user's side of a DM
— build AI conversation history from transcripts instead of channel
history.
## Example app (`examples/nextjs-chat`)
- Plain `SLACK_BOT_TOKEN` adapter branch (previously Slack was only
wired via Vercel Connect).
- DM AI history built from transcripts instead of channel history (see
docs callout above); assistant turns persisted.
- The `dm me` trigger regex now matches mention text, which carries the
`@bot` prefix on Slack.
## Test plan
- `pnpm validate` and `pnpm konsistent` pass.
- Unit tests cover the new events, entity normalization (including
malformed payloads), `agent_view` DM threading, the openDM subscription
bridge, `tab` passthrough, `setSuggestedPrompts` thread handling, and
env-fallback behavior; an integration replay test exercises the full
webhook flow.
- Verified manually against a live `agent_view` workspace:
`onAppContextChanged` entities, folded context on `app_home_opened` and
DM messages, `tab` values for both tabs, per-message DM threading, the
openDM subscription bridge, and signed malformed-payload replays (all
return 200).
- Legacy regression pass with `agentView` off: conversation-scoped DM
threading, Home-tab-only `app_home_opened`, mention flow unchanged.
### Slack references
- Agent messaging experience:
https://docs.slack.dev/changelog/2026/06/30/agent-messages-tab/
- Active-view context:
https://docs.slack.dev/changelog/2026/07/02/app-context/
## Checklist
- [x] All commits are signed and verified
- [x] All commits are signed off for the DCO (`git commit -s`)
- [x] `pnpm validate` passes
- [x] Changeset added
- [x] Documentation updated
---------
Signed-off-by: Damian Borowy <301205838+damianborowy-nexos@users.noreply.github.com>
Signed-off-by: Ben Sabic <bensabic@users.noreply.github.com>
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
## summary
- swap chat model strings to `xai/grok-4.5` across the docs site, the
shipped guides, and the example bots, so the docs lead with the latest
model
- apps/docs: ai overview, ai-sdk-tools, and streaming pages, the two
landing-page code samples, and the live chat demo route
(`app/api/chat/route.ts`, previously `openai/gpt-4.1-mini`)
- packages/chat/resources/guides: the seven guides that use a chat model
(slack connect, slack + ai sdk, liveblocks, vercel blob, github code
review, daily digest, ai gateway)
- examples: nextjs-chat and nuxt-chat bots
- deliberately left non-chat model strings as they were, since grok-4.5
cannot fill those roles: the `openai/text-embedding-3-small` embedding
model and the `openai/gpt-4o-mini` reranker
- in the ai gateway guide, grok-4.5 is now the primary model but the
fallback list stays cross-provider (`anthropic/claude-opus-4.8`,
`google/gemini-3.1-pro-preview`) so the failover example still
demonstrates real cross-provider fallback
- also fixed a pre-existing prose/code mismatch in that guide, the
fallback prose said `claude-opus-4.7` while the code listed `4.8`, now
aligned to `4.8`
---------
Signed-off-by: dancer <josh@afterima.ge>
This PR was opened by the [Changesets
release](https://github.com/changesets/action) GitHub action. When
you're ready to do a release, you can merge this and the packages will
be published to npm automatically. If you're not ready to do a release
yet, that's fine, whenever you add more changesets to main, this PR will
be updated.
# Releases
## @chat-adapter/github@4.33.0
### Minor Changes
- 6750d59: Add Vercel Connect support to the GitHub adapter. A new
`installationToken` config option (string or resolver) supplies
installation access tokens directly, skipping the GitHub App private-key
JWT exchange, and an optional `webhookVerifier` verifies inbound
webhooks (e.g. Connect trigger-forwarded requests via a Vercel OIDC
token) in place of the GitHub webhook secret. Pair with
`connectGitHubAdapter()` from `@vercel/connect/chat`.
`botUserId` now also auto-detects from the `GITHUB_BOT_USER_ID` env var,
and the adapter learns its bot user id from the first comment it posts.
In Connect mode (where the bot user id can't be auto-detected from an
installation token) set `botUserId` / `GITHUB_BOT_USER_ID` to enable
self-message detection and avoid the adapter replying to its own
comments.
Note: the `connectGitHubAdapter()` helper ships in `@vercel/connect` —
release this adapter together with (or after) the `@vercel/connect`
version that adds the `@vercel/connect/chat` subpath so the documented
helper resolves.
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/linear@4.33.0
### Minor Changes
- 4115c94: Add Vercel Connect support to the Linear adapter. The
`accessToken` config option now accepts a resolver (`() => string |
Promise<string>`) in addition to a string, so tokens can be sourced from
Vercel Connect at runtime, and a new optional `webhookVerifier` verifies
inbound webhooks (e.g. Connect trigger-forwarded requests via a Vercel
OIDC token) in place of the Linear webhook secret. Pair with
`connectLinearAdapter()` from `@vercel/connect/chat`. Connect-mode
outbound calls outside webhook handling are supported via
`withInstallation(organizationId, fn)`.
Note: the `connectLinearAdapter()` helper ships in `@vercel/connect` —
release this adapter together with (or after) the `@vercel/connect`
version that adds the `@vercel/connect/chat` subpath so the documented
helper resolves.
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/shared@4.33.0
### Minor Changes
- d4c52ca: add `replaceBareMentions`, a context-aware bare-`@mention`
resolver that skips code spans, URLs, schemeless hosts, and existing
angle-bracket tokens before handing each real `@name` to a
platform-specific replacer
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [076fe5d]
- chat@4.33.0
## @chat-adapter/x@4.33.0
### Minor Changes
- ef2542c: add X (Twitter) adapter: reply to public mentions, send and
receive direct messages, post and edit from the bot account, and like
posts, using the X API v2 with OAuth 2.0 and managed token refresh
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## chat@4.33.0
### Minor Changes
- ef2542c: add X (Twitter) adapter: reply to public mentions, send and
receive direct messages, post and edit from the bot account, and like
posts, using the X API v2 with OAuth 2.0 and managed token refresh
### Patch Changes
- 3abdc69: docs(adapters): add Cloudflare Agents as a vendor-official
state adapter (`agents/chat-sdk`) to the catalog and docs listing. It is
hidden from the create-chat-sdk CLI (Worker/Durable Objects runtime),
and the interactive state picker now filters out CLI-incompatible state
adapters.
- 0b63791: Raise the default message dedupe TTL from 5 to 10 minutes so
it outlives the longest platform redelivery window. Slack's Events API
retries up to ~5 minutes after the original delivery — exactly at the
old TTL boundary, where a retried event could miss the expired dedupe
entry from its first processing and be handled twice. Configurable
behavior is unchanged (`dedupeTtlMs` still overrides).
- 0c761f1: docs(adapters): add Dial as a vendor-official adapter
(`@getdial/chat-sdk-adapter`) to the catalog, docs listing, and CLI
scaffold spec
- 24a04d5: docs(adapters): add Photon as a vendor-official adapter
(`@photon-ai/chat-adapter-imessage`) to the catalog, docs listing, and
CLI scaffold spec
- 076fe5d: preserve skipped mention routing for debounce and message
patterns
## create-chat-sdk@0.2.0
### Minor Changes
- ba375ce: Add Vercel Connect support to the scaffolder. Pass
`--connect` (or choose **Vercel Connect** at the new interactive
auth-mode prompt) to authenticate the Slack, GitHub, and Linear adapters
with a Vercel Connect connector instead of stored provider secrets. The
generated `src/lib/bot.ts` spreads the matching helper from
`@vercel/connect/chat` into the adapter factory, `@vercel/connect` is
added to dependencies, and `.env.example` lists each connector UID (for
example `SLACK_CONNECTOR`) plus the recommended `GITHUB_BOT_USER_ID` for
GitHub, in place of native secrets.
- ef2542c: add X (Twitter) adapter: reply to public mentions, send and
receive direct messages, post and edit from the bot account, and like
posts, using the X API v2 with OAuth 2.0 and managed token refresh
### Patch Changes
- 3abdc69: docs(adapters): add Cloudflare Agents as a vendor-official
state adapter (`agents/chat-sdk`) to the catalog and docs listing. It is
hidden from the create-chat-sdk CLI (Worker/Durable Objects runtime),
and the interactive state picker now filters out CLI-incompatible state
adapters.
- 0c761f1: docs(adapters): add Dial as a vendor-official adapter
(`@getdial/chat-sdk-adapter`) to the catalog, docs listing, and CLI
scaffold spec
- 24a04d5: docs(adapters): add Photon as a vendor-official adapter
(`@photon-ai/chat-adapter-imessage`) to the catalog, docs listing, and
CLI scaffold spec
## @chat-adapter/tests@4.33.0
### Minor Changes
- e7a396a: Add two shared behavioral test contracts for adapter authors:
- `threadIdContract` — verifies an adapter's thread-id codec round-trips
(`decode(encode(x))`), prefixes ids with the adapter name, matches any
pinned encoded strings, and (optionally) distinguishes DM from non-DM
threads.
- `selfMessageContract` — verifies an adapter dispatches inbound
messages from other users (to `processMessage` by default) but ignores
messages the bot authored itself, so it never replies to itself.
Requires the matchers to be registered via `setupFiles:
["@chat-adapter/tests/setup"]`.
- a7fb1bc: Add `connectWebhookContract`, a shared Vitest suite for
verifying an adapter's Vercel Connect webhook verification. Given a
small per-adapter descriptor (how to build the adapter in Connect mode
and craft an inbound webhook), it asserts the behavior every
Connect-capable adapter shares: a `webhookVerifier` replaces the native
signature/secret check and gates inbound requests — accept (`200`) on a
truthy result, reject (`401`) on a thrown error or falsy result — and is
invoked with the request and raw body. Connect-capable adapters can opt
in with ~10 lines.
## @chat-adapter/discord@4.33.0
### Patch Changes
- d4c52ca: use the shared `replaceBareMentions` scanner for `@mention`
conversion so email addresses, `@handles` inside URLs, and mentions
inside code spans are no longer mangled into Discord mentions, and
already-formatted `<@id>` tokens are not double-wrapped
- 6de4572: Implement `rehydrateAttachment` on the Discord adapter.
Serialization strips an attachment's `fetchData` closure (queue/debounce
strategies), and consumers rebuild it via `adapter.rehydrateAttachment`.
The Discord adapter did not implement the method, so downstream
consumers could not download inbound Discord attachments after
deserialization. The Discord CDN `url` survives serialization, so
`fetchData` is now rebuilt to fetch that url (preserving its signed
query params), matching how the other adapters implement the method.
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/gchat@4.33.0
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/messenger@4.33.0
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/slack@4.33.0
### Patch Changes
- 0b63791: Process Slack Socket Mode retry envelopes instead of
discarding them. Slack redelivers an event (immediately, +1 min, +5 min)
when a prior delivery wasn't acknowledged — including events sent while
the app had no open socket, e.g. during a restart or a routine
connection refresh. The adapter previously acked and dropped every
envelope with `retry_num > 0`, so such events were permanently lost even
though Slack redelivered them. Retries are now routed like first
deliveries (logged at info with `retry_num`/`retry_reason`);
`Chat.processMessage`'s message-id dedupe drops true duplicates.
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/teams@4.33.0
### Patch Changes
- d4c52ca: use the shared `replaceBareMentions` scanner for `@mention`
conversion so email addresses, `@handles` inside URLs, and mentions
inside code spans are no longer mangled into `<at>` mention tags
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/telegram@4.33.0
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/twilio@4.33.0
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/web@4.33.0
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/whatsapp@4.33.0
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [d4c52ca]
- Updated dependencies [076fe5d]
- chat@4.33.0
- @chat-adapter/shared@4.33.0
## @chat-adapter/state-ioredis@4.33.0
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [076fe5d]
- chat@4.33.0
## @chat-adapter/state-memory@4.33.0
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [076fe5d]
- chat@4.33.0
## @chat-adapter/state-pg@4.33.0
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [076fe5d]
- chat@4.33.0
## @chat-adapter/state-redis@4.33.0
### Patch Changes
- Updated dependencies [3abdc69]
- Updated dependencies [0b63791]
- Updated dependencies [0c761f1]
- Updated dependencies [ef2542c]
- Updated dependencies [24a04d5]
- Updated dependencies [076fe5d]
- chat@4.33.0
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
## summary
new `@chat-adapter/x` adapter for X (Twitter), built on the X API v2 and
the X Activity API. write bot logic once and reply to mentions, hold DM
conversations, post from the account, and like posts, like the other
Chat SDK adapters
what it supports:
- reply to public mentions (`post.mention.create`) and top-level posts
via `channel.post`
- send and receive direct messages (`dm.received` / `dm.sent`)
- edit and delete owned posts, delete own DM events
- likes as the only reaction (`emoji.heart` or `"like"`)
- buffered streaming: accumulates an LLM stream and posts once instead
of post+edit churn on a public timeline
- OAuth 2.0 user context with managed token refresh (rotating refresh
token persisted in the state adapter, optional AES-256-GCM encryption)
- webhook CRC and `x-twitter-webhooks-signature` verification
key design decisions:
- DMs are threaded by the other participant's user id (`x:dm:{userId}`)
because X DM webhooks carry no conversation id, only participants
- OAuth 2.0 only at runtime: DM send and read are verified to work on
OAuth 2.0 user tokens, so no OAuth 1.0a in the adapter (subscription and
webhook setup is one-time and handled in the X developer console)
- parsers were written against real captured payloads: mentions use the
v2 shape (author hydrated in `includes.users`), DMs use the legacy
Account Activity shape (`direct_message_events`,
`message_create.message_data`, a `users` map, and no conversation id)
also includes the `chat/adapters` catalog entry, docs page, CLI scaffold
spec, and `sample-messages.md` with real captured payloads
<details><summary>usage</summary>
```typescript
import { Chat } from "chat";
import { createXAdapter } from "@chat-adapter/x";
const bot = new Chat({
userName: "mybot",
adapters: { x: createXAdapter() },
});
bot.onNewMention(async (thread, message) => {
await thread.post(`hi @${message.author.userName}!`);
});
bot.onDirectMessage(async (thread) => {
await thread.post("hello from X");
});
```
</details>
## test plan
- adapter unit tests pass against the real captured payload shapes, with
regression tests for author-from-`includes` (mentions) and the legacy
`direct_message_events` shape (DMs)
- real captured `post.mention.create` and `dm.received` payloads
verified end-to-end through `handleWebhook`: signature verification,
routing, author resolution, and participant threading, plus
bad-signature rejection returns 401
- every write and read path fired live against the X API through the
adapter: top-level post, reply to a mention, like and unlike, edit,
delete, DM send, DM read, DM delete
- OAuth 2.0 managed token refresh exercised live (access and refresh
token rotation)
---------
Signed-off-by: dancer <josh@afterima.ge>
Adds Dial as a vendor-official adapter — SMS, MMS, iMessage, and inbound
voice-call transcripts for Chat SDK.
- `vendor-official/dial.mdx` adapter page (following the Photon / Linq /
Sendblue format)
- catalog entry in `packages/chat/src/adapters/index.ts` with
`DIAL_API_KEY` / `DIAL_FROM_NUMBER_ID` / `DIAL_WEBHOOK_SECRET`
- `create-chat-sdk` scaffold spec entry
- registry entry in `adapters.json` + `dial` added to vendor-official
`meta.json`
- integration-test doc lists + changeset
Repo: https://github.com/GetDial-AI/chat-sdk-adapter · npm:
`@getdial/chat-sdk-adapter` · Dial docs:
https://docs.getdial.ai/integrations/agent-clients/vercel-chat-sdk
The adapter maps a phone conversation to a Chat SDK thread (identified
by the pair of phone numbers — Dial-owned and peer), an SMS/MMS/iMessage
to a message with optional media attachments, and a completed voice
call's transcript to a message on the caller's thread. Outbound sends
and transcript fetches go through the official `@getdial/sdk`; inbound
webhooks are HMAC-SHA256 verified against a per-subscription signing
secret with constant-time compare.
### Validation
- `pnpm --filter chat build` — clean
- `pnpm --filter chat typecheck` — clean
- `pnpm --filter create-chat-sdk typecheck` — clean
- `pnpm --filter @chat-adapter/integration-tests exec vitest run
src/docs-adapters.test.ts` — 361/361 passed
- `pnpm check` (ultracite) — clean
- `pnpm konsistent` — 34 files, no violations
Fixes#666
## Summary
Both `slack_event` handlers (`startSocketMode` and
`runSocketModeListener`) ack and discard every envelope with `retry_num
> 0`. Slack retries an event (immediately, +1 min, +5 min) when a prior
delivery wasn't acked — including events that arrived while the app had
**no open socket** (restart, deploy, or Slack's routine connection
refreshes). For those, the retry is the only delivery the app ever sees,
so dropping it permanently loses the event (production incident details
in #666).
- **`@chat-adapter/slack`**: route retry envelopes through
`routeSocketEvent` like first deliveries (it acks per envelope type,
preserving the 3s ack window), and log them at info with `retry_num` /
`retry_reason` so redelivery is observable. Duplicate protection is
unchanged and sufficient: `Chat.processMessage` dedupes on `message.id`
(the Slack event `ts`, identical on a retry) via `state.setIfNotExists`.
- **`chat`**: raise the default `DEDUPE_TTL_MS` from 5 to 10 minutes.
Slack's final retry fires ~5 minutes after the original delivery —
exactly at the old TTL boundary, where the dedupe entry from the first
processing could expire just before the retry arrives and cause a
double-process. `dedupeTtlMs` config still overrides.
Behavior note for review: apps that relied on retries being invisible
will now see redelivered events flow through — deduped when already
handled, processed when not. That is the intended semantic:
at-least-once delivery from Slack, exactly-once handling via the SDK's
dedupe.
## Test plan
- Replaced the `"skips retries"` test with `"processes retries like
first deliveries (dedupe drops true duplicates)"` — asserts a
`retry_num: 1` envelope is acked and reaches `processMessage`.
- Updated the default-TTL test to 10 minutes; the custom-`dedupeTtlMs`
test is unchanged.
- `pnpm validate` passes end to end (knip, check, typecheck, test,
build); `pnpm --filter chat --filter @chat-adapter/slack test` = 1028 +
506 passing.
Signed-off-by: tdietert <thomasd@mercury.com>
Adds Cloudflare Agents as a vendor-official **state** adapter —
`agents/chat-sdk`'s `createChatSdkState()`, a Chat SDK `StateAdapter`
that stores subscriptions, locks, queues, dedupe keys, thread/channel
state, transcripts, and history in Durable Object SQLite via
`ChatSdkStateAgent` sub-agents.
- `vendor-official/cloudflare-agents.mdx` state-adapter page (Agent
setup, wrangler DO migration, sharding, config, storage/cleanup)
- catalog entry in `packages/chat/src/adapters/index.ts` (`group:
vendor-official`, `type: state`)
- registry entry in `adapters.json` + `cloudflare-agents` in
vendor-official `meta.json`
- integration-test doc lists + changeset
Repo: https://github.com/cloudflare/agents · package `agents`
(`agents/chat-sdk`) ·
[docs](https://developers.cloudflare.com/agents/runtime/communication/chat-sdk/)
### Not wired into the create-chat-sdk CLI
This adapter runs inside a Cloudflare Worker with Durable Objects, not
the generated Next.js runtime, so it is intentionally kept out of the
scaffold:
- added to `CLI_INCOMPATIBLE_ADAPTERS` (rejected via `--adapter`, hidden
from the platform picker and e2e run, like `lark`/`matrix`)
- new `listCliStateAdapters()` filters the interactive **state** picker
and the `--help` adapter list (the state picker previously used raw
`listStateAdapters()` and would have offered it, then thrown on
selection)
### Tests
- `catalog/display.test.ts` — `listCliStateAdapters`: returns only state
adapters, includes `memory`/`redis`, and excludes `cloudflare-agents`
while asserting it *is* in the raw catalog
- `catalog/selection.test.ts` —
`resolveAdapterValue("cloudflare-agents")` throws "not supported"
- `cli/program.test.ts` — `buildAdapterList()` help text omits
`cloudflare-agents`
- existing `CLI_SCAFFOLD_SPEC covers every catalog adapter` +
docs-adapters/docs-content suites cover the catalog entry, registry
parity, and MDX imports
### Validation
- create-chat-sdk: **178 passed**, typecheck clean
- integration docs suites pass; Biome + knip clean
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
Adds Vercel Connect support to the GitHub adapter:
- A new `installationToken` config option (string or resolver) supplies
installation access tokens directly, skipping the GitHub App private-key
JWT exchange.
- A new optional `webhookVerifier` verifies inbound webhooks (Connect
trigger-forwarded requests via a Vercel OIDC token) in place of the
GitHub webhook secret.
Pair with `connectGitHubAdapter()` from `@vercel/connect/chat`. Includes
a changeset (`@chat-adapter/github` minor).
Stacked on #647 (base `vercel-connect/base`).
## Companion
`@vercel/connect/chat` subpath: vercel/vercel#16826.
<img width="933" height="755" alt="CleanShot 2026-06-30 at 12 02 18"
src="https://github.com/user-attachments/assets/cc834560-0486-4f09-b8d5-8264be360544"
/>
---------
Signed-off-by: Ben Sabic <bensabic@users.noreply.github.com>
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
## summary
fixes skipped mention routing for collapsed concurrency messages
queue and burst already passed skipped message context, but mention
routing could still swallow message pattern handlers when no
`onNewMention` handler was registered
this also makes debounce preserve skipped context so an earlier
debounced bot mention can still route to `onNewMention` when the latest
message does not mention the bot
## Summary
Plan’s task list API always marked existing in-progress steps as
complete whenever a new step was added. That made sense for simple
sequential bots, but it blocked parallel work — even though the docs
already showed a parallel pattern and per-task updates by ID were added
earlier.
This PR adds an optional flag on task creation so callers can keep
multiple steps in progress at once, while leaving the old sequential
behavior as the default.
**Opt-out flag, default on**. We considered removing auto-completion
entirely. That would’ve been cleaner for parallel use but would’ve
broken existing sequential bots that rely on implicit “move to next
step” behavior. Defaulting to the current behavior keeps upgrades safe;
parallel callers pass the flag off.
**No broader API redesign**. Task completion stays explicit via status
updates and the existing “complete plan” flow. The change is scoped to
when a new task is appended.
closes#630
## summary
fixes#613
detects bot mentions across queued and burst skipped messages before
routing handlers
this makes `onNewMention` fire when an earlier skipped message mentions
the bot and the latest collapsed message does not, while preserving
`message.isMention` on the latest message
adds regression coverage for both `queue` and `burst`
- Replace npm version/download badges with Agent Stack and MIT badges on
the root README and all published package READMEs
- Streamline root `AGENTS.md`: fix title, add an accurate monorepo map,
trim duplicated CONTRIBUTING/Ultracite/env-var content, and link to
package-level `AGENTS.md` files
- Slim the Chat SDK agent skill (`skills/chat/SKILL.md` and published
copies) to defer to bundled docs, chat-sdk.dev, Vercel KB, and
`llms.txt` instead of inlining CLI flags, quick-start code, and API
tables
- Polish root README copy (install examples, adapter/build links, Vercel
Plugin URL, Vercel KB link, “Made by Vercel” badge)
- Minor `CONTRIBUTING.md` fixes: simplify DCO wording, correct
preview-branch proxy file references (`proxy.ts` vs middleware)
---------
Signed-off-by: Ben Sabic <bensabic@users.noreply.github.com>
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
## summary
fixes#631
removes dummy `Message` casts from lightweight thread, action, and
reaction paths when no incoming message context exists
this keeps the existing `currentMessage` guard meaningful and prevents
streaming through `chat.thread(threadId)`, `chat.openDM(...)`, action
threads, and reaction threads from reading fields from an empty object
when Slack lacks the thread or recipient context required by
`chat.startStream`, the adapter now returns `null` before consuming the
stream so Chat SDK can transparently use its post-and-edit fallback
native Slack streaming remains available for webhook-created threads and
DM threads with valid native stream context
---------
Co-authored-by: dancer <josh@afterima.ge>
Syncs the bundled Chat SDK KB resources from Edge Config and hardens the
`sync-resources` script that generates them.
- **New guides** (4): Vercel Connect, the Slack Vercel Connect bot, AI
Gateway + AI SDK, and the daily digest bot. Existing guide bodies
refreshed and `templates.json` regenerated.
- **Script hardening** (`scripts/sync-resources.ts`):
- Fetch + validate all guides into memory **before** wiping the
resources dir — a failed fetch now leaves the working tree untouched.
- Validate the `resources-edge-config.json` shape with a clear error
instead of a blind cast.
- Reject duplicate guide slug collisions.
- Retry transient fetches (5xx / network) with exponential backoff; fail
fast on 4xx, bad content-type, and oversized bodies.
- Mirror `skills/chat/SKILL.md` to **all four** committed copies (docs
site `.well-known` + `AGENTS.md`, and the two `create-chat-sdk` scaffold
templates).
- TSDoc on every function.
- **Tests**: new offline consistency test in
`packages/integration-tests` — every guide has a non-empty file with no
orphans, `templates.json` mirrors the config, no duplicate slugs, and
all four `SKILL.md` copies are byte-identical to the source.
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
Adds Linq as a vendor-official adapter — iMessage and SMS for Chat SDK.
- `vendor-official/linq.mdx` adapter page (following the Velt /
AgentPhone format)
- catalog entry in `adapters.json`
- `linq` added to the vendor-official `meta.json`
Repo: https://github.com/linq-team/linq-chat-sdk · npm:
`@linqapp/chat-sdk-adapter` (Apache-2.0)
The adapter is built and tested end-to-end against the live Linq API and
the Chat SDK runtime (real iMessage round-trip, webhooks, reactions,
media). Confirmed with Benji that a repo link works and Apache-2.0 is
fine. Happy to adjust the page to match any conventions I missed.
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
## Summary
Adds Novu as a vendor official adapter to Chat SDK allowing
multi-channel notification delivery and quick channel setup for
multi-tenant apps.
Official change log entry:
https://novu.co/changelog/novu-chat-sdk-adapter/
Official social post: https://x.com/novuhq/status/2067870170320679158
## Test plan
Manually tested with our team to ensure compatability with the create
chat sdk and template apps, also created an example repo:
https://github.com/novuhq/novu-chat-sdk-example
## Checklist
- [x] All commits are signed and verified
- [x] `pnpm validate` passes
- [x] Changeset added (or N/A — see
[CONTRIBUTING.md](./CONTRIBUTING.md))
- [x] Documentation updated (or N/A)
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
Adds `create-chat-sdk`, a CLI that scaffolds a Next.js Chat SDK bot
project:
```bash
npm create chat-sdk@latest my-bot
# non-interactive
npm create chat-sdk@latest -- my-bot --adapter slack redis -y
```
The user picks platform and state adapters interactively or via
`--adapter`, and the CLI generates a webhook-only project with
`src/lib/bot.ts`, `.env.example`, `next.config.ts`, `package.json`, and
a README, then optionally runs `git init` and installs dependencies.
There are no pages or client UI in the template.
Adapter choices come straight from the `chat/adapters` catalog, so the
CLI has no adapter registry of its own. When a coding agent such as
Cursor or Claude Code runs the CLI, it uses non-interactive defaults and
requires an explicit platform adapter. `--interactive` forces prompts.
## also in this pr
- `google-chat` is renamed to `gchat` everywhere, including docs pages,
the OG image, and adapter catalog. Old URLs redirect permanently,
including language-prefixed and `/og` paths
- a new docs page is available at `chat-sdk.dev/docs/create-chat-sdk`,
and the CLI is promoted on the homepage, package READMEs, and agent
skill
- `create-chat-sdk` releases independently with a minor changeset for
its initial `0.1.0` release
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
Co-authored-by: dancer <josh@afterima.ge>
Adapter Catalog:
- Adds a zero-dependency `chat/adapters` subpath for official and
vendor-official adapter metadata.
- Includes typed catalog entries, env specs, peer dependency metadata,
and helper APIs for setup and onboarding flows.
- Wires the subpath into the `chat` package export map and build config.
Code Coverage:
- Adds unit coverage for catalog integrity, registry sync, helper
behavior, official env declarations, and peer dependency derivation.
- Extends docs integration coverage for `chat/adapters` imports and
vendor-official package install metadata.
Documentation:
- Documents the new catalog on the adapter overview page.
- Splits platform-specific adapter guidance into a new
`/docs/platform-adapters` page.
- Renames `/docs/state` to `/docs/state-adapters` and adds a redirect
for the old slug.
Agent Guidance:
- Updates repo-local and public agent guidance so agents know when and
how to use `chat/adapters`.
- Adds focused `AGENTS.md` guidance inside `packages/chat/src/adapters`
for future catalog maintenance.
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
Improves Chat SDK discoverability across npm, READMEs, and the docs site
for search engines and AI coding agents.
- **npm metadata**: point every published package `homepage` at
chat-sdk.dev deep links; expand `chat` keywords/description; fix
`repository.directory` (`packages/chat-sdk` → `packages/chat`); align
state adapter keywords
- **READMEs**: add npm callouts, Documentation/Guides links, and AI
Coding Agents sections (skill install, optional Vercel Plugin,
`llms.txt` / `llms-full.txt`) across all published packages and the repo
root
- **docs JSON-LD**: `HowTo` / `TechArticle` on getting-started,
streaming, and cards; `CollectionPage` + official-only `ItemList` on
`/adapters` (with split human vs JSON-LD descriptions)
- **UTMs**: add `chat-sdk_site` / `chat-sdk_repo` tracking params to
Resources links in selected MDX pages and adapter READMEs (discord,
github, slack, liveblocks, getting-started, ai index)
- **contract tests**: integration-tests guardrails for npm metadata and
README discoverability so future package additions don't drift
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
## summary
clarifies that `author.isMe` means the message was sent by the current
bot runtime and should be filtered from handler dispatch
documents that adapters backed by user-owned accounts should not map
platform fields like `fromMe` directly to `isMe`
recommends tracking message ids returned by `postMessage` so webhook
echoes can be identified without filtering legitimate user-authored
messages
Broad SEO/AEO pass across the docs site, adapter READMEs and AGENTS.md
files, and npm package metadata so Chat SDK content shows up better in
search engines, in LLM-driven package recommendations, and in
IDE/coding-agent context.
**Docs site**
- Adds a `## Resources` section to the Getting Started and AI overview
pages and to the Slack, Discord, GitHub, Liveblocks, and Sendblue
adapter pages, each linking to applicable guides/templates with
descriptions sourced from `resources-edge-config.json` and a cross-link
back to the central `/resources` hub.
**Adapter packages**
- Mirrors the same Resources sections into the Slack, Discord, and
GitHub READMEs (so they surface on npm) and into their AGENTS.md files
(so coding agents see them alongside the API notes).
- Expands `keywords` on every published adapter and state package — adds
`chat-sdk`, `chatbot`, `ai-agent`, `ai-sdk`, `vercel`, plus
platform-specific terms like `slack-bot`, `block-kit`, `slash-commands`,
`github-app`, `whatsapp-business`, `state-adapter`.
**Resources registry**
- Registers four new entries in `resources-edge-config.json`
(Human-in-the-Loop guide, Liveblocks AI agent guide, Slack + Vercel Blob
guide, Durable iMessage Agent template) and runs `pnpm sync-resources`
so the bundled `chat` package guides, `templates.json`, and
`skills/chat/SKILL.md` all pick them up.
- Fixes the synced Slack AI agent guide to import `toAiMessages` from
`chat/ai` instead of the deprecated `chat` re-export path (the upstream
KB source has also been updated, so future syncs will preserve this).
**Drive-by fixes**
- Resend adapter doc quick start: corrects `MemoryStateAdapter` class
import to the `createMemoryState()` factory (matching every other
adapter doc).
- Zalo adapter doc: drops the "community adapter" callout that
duplicated frontmatter.
**Tooling / CI**
- Adds `tsx` as a root devDependency so `pnpm sync-resources` works out
of the box (it previously relied on `npx tsx`, which hung when not
pre-cached).
- Loosens the CI changeset gate to also skip `packages/chat/resources/`
(generated data), matching the existing `*.md` carve-out.
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
This PR was opened by the [Changesets
release](https://github.com/changesets/action) GitHub action. When
you're ready to do a release, you can merge this and the packages will
be published to npm automatically. If you're not ready to do a release
yet, that's fine, whenever you add more changesets to main, this PR will
be updated.
# Releases
## @chat-adapter/discord@4.29.0
### Minor Changes
- 2ffed48: Adapter internals are now `protected` rather than `private`,
so consumers can subclass an adapter to override or extend its behavior
(e.g. handling additional Telegram update types by overriding
`processUpdate`).
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- b9b17cd: handle slash commands and button interactions in Discord
gateway-only mode
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [add2730]
- Updated dependencies [b75eedb]
- chat@4.29.0
- @chat-adapter/shared@4.29.0
## @chat-adapter/gchat@4.29.0
### Minor Changes
- 2ffed48: Adapter internals are now `protected` rather than `private`,
so consumers can subclass an adapter to override or extend its behavior
(e.g. handling additional Telegram update types by overriding
`processUpdate`).
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- 06fb8e5: Align package shapes with the new `konsistent` conventions.
All changes are
backwards-compatible — previous type names are kept as deprecated
aliases.
- `@chat-adapter/gchat`, `@chat-adapter/slack`: moved `*AdapterConfig`
(and
related sub-types) into a `./types` module; the public re-exports from
`index.ts` are unchanged.
- `@chat-adapter/slack`: `createSlackAdapter` now accepts
`SlackAdapterConfig`
directly instead of `Partial<SlackAdapterConfig>`. Every field on the
config
was already optional, so no call sites need to change.
- `@chat-adapter/messenger`: `MessengerAdapterConfig` fields are now
optional
(the factory still falls back to `FACEBOOK_*` env vars), and `logger` /
`userName` live on `MessengerAdapterConfig` directly. The factory
signature
is now `createMessengerAdapter(config?: MessengerAdapterConfig)`.
- `@chat-adapter/web`: renamed `WebAdapterOptions` to
`WebAdapterConfig`; the
old name is exported as a deprecated alias.
- `@chat-adapter/whatsapp`: every field on `WhatsAppAdapterConfig` is
optional
(the factory still falls back to `WHATSAPP_*` env vars).
`createWhatsAppAdapter`
is now typed `(config?: WhatsAppAdapterConfig) => WhatsAppAdapter`.
- `@chat-adapter/state-memory`: added an empty
`MemoryStateAdapterOptions`
type so the package matches every other state adapter;
`createMemoryState`
now accepts an optional argument of that type.
- `@chat-adapter/state-ioredis`, `@chat-adapter/state-redis`,
`@chat-adapter/state-pg`: the URL- and client-based option shapes were
split
into named interfaces (`*StateAdapterUrlOptions` /
`*StateAdapterClientOptions`) and unified under `*StateAdapterOptions`.
The
factories now take the union type directly. Old names —
`RedisStateClientOptions`,
`CreateRedisStateOptions`, `PostgresStateClientOptions`,
`CreatePostgresStateOptions`, `IoRedisStateClientOptions` — are kept as
deprecated aliases.
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [add2730]
- Updated dependencies [b75eedb]
- chat@4.29.0
- @chat-adapter/shared@4.29.0
## @chat-adapter/github@4.29.0
### Minor Changes
- 2f108bd: Rename the typed native client getter on the Slack, GitHub,
and Linear adapters to match the underlying SDK class.
- `bot.getAdapter("slack").client` is now
`bot.getAdapter("slack").webClient` (returns `WebClient` from
`@slack/web-api`).
- `bot.getAdapter("github").client` is now
`bot.getAdapter("github").octokit` (returns `Octokit`).
- `bot.getAdapter("linear").client` is now
`bot.getAdapter("linear").linearClient` (returns `LinearClient`).
The previous `.client` getter is kept as a deprecated alias on all three
adapters, so existing code continues to work without changes.
- 2ffed48: Adapter internals are now `protected` rather than `private`,
so consumers can subclass an adapter to override or extend its behavior
(e.g. handling additional Telegram update types by overriding
`processUpdate`).
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [add2730]
- Updated dependencies [b75eedb]
- chat@4.29.0
- @chat-adapter/shared@4.29.0
## @chat-adapter/linear@4.29.0
### Minor Changes
- 2f108bd: Rename the typed native client getter on the Slack, GitHub,
and Linear adapters to match the underlying SDK class.
- `bot.getAdapter("slack").client` is now
`bot.getAdapter("slack").webClient` (returns `WebClient` from
`@slack/web-api`).
- `bot.getAdapter("github").client` is now
`bot.getAdapter("github").octokit` (returns `Octokit`).
- `bot.getAdapter("linear").client` is now
`bot.getAdapter("linear").linearClient` (returns `LinearClient`).
The previous `.client` getter is kept as a deprecated alias on all three
adapters, so existing code continues to work without changes.
- 2ffed48: Adapter internals are now `protected` rather than `private`,
so consumers can subclass an adapter to override or extend its behavior
(e.g. handling additional Telegram update types by overriding
`processUpdate`).
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [add2730]
- Updated dependencies [b75eedb]
- chat@4.29.0
- @chat-adapter/shared@4.29.0
## @chat-adapter/messenger@4.29.0
### Minor Changes
- 2ffed48: Adapter internals are now `protected` rather than `private`,
so consumers can subclass an adapter to override or extend its behavior
(e.g. handling additional Telegram update types by overriding
`processUpdate`).
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- 06fb8e5: Align package shapes with the new `konsistent` conventions.
All changes are
backwards-compatible — previous type names are kept as deprecated
aliases.
- `@chat-adapter/gchat`, `@chat-adapter/slack`: moved `*AdapterConfig`
(and
related sub-types) into a `./types` module; the public re-exports from
`index.ts` are unchanged.
- `@chat-adapter/slack`: `createSlackAdapter` now accepts
`SlackAdapterConfig`
directly instead of `Partial<SlackAdapterConfig>`. Every field on the
config
was already optional, so no call sites need to change.
- `@chat-adapter/messenger`: `MessengerAdapterConfig` fields are now
optional
(the factory still falls back to `FACEBOOK_*` env vars), and `logger` /
`userName` live on `MessengerAdapterConfig` directly. The factory
signature
is now `createMessengerAdapter(config?: MessengerAdapterConfig)`.
- `@chat-adapter/web`: renamed `WebAdapterOptions` to
`WebAdapterConfig`; the
old name is exported as a deprecated alias.
- `@chat-adapter/whatsapp`: every field on `WhatsAppAdapterConfig` is
optional
(the factory still falls back to `WHATSAPP_*` env vars).
`createWhatsAppAdapter`
is now typed `(config?: WhatsAppAdapterConfig) => WhatsAppAdapter`.
- `@chat-adapter/state-memory`: added an empty
`MemoryStateAdapterOptions`
type so the package matches every other state adapter;
`createMemoryState`
now accepts an optional argument of that type.
- `@chat-adapter/state-ioredis`, `@chat-adapter/state-redis`,
`@chat-adapter/state-pg`: the URL- and client-based option shapes were
split
into named interfaces (`*StateAdapterUrlOptions` /
`*StateAdapterClientOptions`) and unified under `*StateAdapterOptions`.
The
factories now take the union type directly. Old names —
`RedisStateClientOptions`,
`CreateRedisStateOptions`, `PostgresStateClientOptions`,
`CreatePostgresStateOptions`, `IoRedisStateClientOptions` — are kept as
deprecated aliases.
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [add2730]
- Updated dependencies [b75eedb]
- chat@4.29.0
- @chat-adapter/shared@4.29.0
## @chat-adapter/shared@4.29.0
### Minor Changes
- add2730: support typed Telegram attachment uploads
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [b75eedb]
- chat@4.29.0
## @chat-adapter/slack@4.29.0
### Minor Changes
- 2f108bd: Rename the typed native client getter on the Slack, GitHub,
and Linear adapters to match the underlying SDK class.
- `bot.getAdapter("slack").client` is now
`bot.getAdapter("slack").webClient` (returns `WebClient` from
`@slack/web-api`).
- `bot.getAdapter("github").client` is now
`bot.getAdapter("github").octokit` (returns `Octokit`).
- `bot.getAdapter("linear").client` is now
`bot.getAdapter("linear").linearClient` (returns `LinearClient`).
The previous `.client` getter is kept as a deprecated alias on all three
adapters, so existing code continues to work without changes.
- c46fdb6: Add support for external `installationProvider` and
Enterprise Grid org-wide installs.
- New optional `installationProvider` config: `{
getInstallation(installationId, isEnterpriseInstall) =>
Promise<SlackInstallation | null> }`. When set, the adapter resolves bot
tokens for incoming events, slash commands, and interactive payloads
through the provider instead of the internal `StateAdapter` — useful for
hosted token-management systems (e.g. Vercel Connect). The provider is
read-only; OAuth callback writes (`setInstallation`,
`handleOAuthCallback`) and the `getInstallation`/`deleteInstallation`
public methods continue to use internal state, so callers using a
provider should manage their own writes.
- Enterprise Grid org-wide installs (`is_enterprise_install: true`) are
now keyed on `enterprise_id` instead of `team_id` across event_callback,
slash command, and interactive payload paths. Multi-workspace
deployments using the internal `StateAdapter` for org-wide installs must
repopulate installations under the `enterprise_id` key — previously,
org-wide events would fall through to a `team_id` lookup that did not
match what the OAuth flow had stored.
- fdebde7: feat(slack): expose direct `WebClient` access via
`adapter.client`
`bot.getAdapter("slack").client` now returns a typed `WebClient` from
`@slack/web-api`, matching the existing pattern on the Linear and GitHub
adapters. The returned client is bound to the bot token for the current
request context (multi-workspace) or the configured default token
(single-workspace). Use it for any Web API call not covered by the SDK's
high-level methods, e.g. `adapter.client.pins.add(...)` or
`adapter.client.usergroups.list(...)`.
Resolution order:
1. The token from the current `requestContext` — set during webhook
handling, or by `adapter.withBotToken(token, fn)`.
2. The default `botToken`, when configured as a static string or a
synchronous resolver function.
Throws `AuthenticationError` outside of any context in multi-workspace
mode, or when `botToken` is configured as an async resolver function.
For async tokens, await the token first and bind it explicitly with
`adapter.withBotToken(token, () => adapter.client...)`.
Also fixes `createSlackAdapter()` silently dropping the `apiUrl`
config field.
- 2ffed48: Adapter internals are now `protected` rather than `private`,
so consumers can subclass an adapter to override or extend its behavior
(e.g. handling additional Telegram update types by overriding
`processUpdate`).
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- 06fb8e5: Align package shapes with the new `konsistent` conventions.
All changes are
backwards-compatible — previous type names are kept as deprecated
aliases.
- `@chat-adapter/gchat`, `@chat-adapter/slack`: moved `*AdapterConfig`
(and
related sub-types) into a `./types` module; the public re-exports from
`index.ts` are unchanged.
- `@chat-adapter/slack`: `createSlackAdapter` now accepts
`SlackAdapterConfig`
directly instead of `Partial<SlackAdapterConfig>`. Every field on the
config
was already optional, so no call sites need to change.
- `@chat-adapter/messenger`: `MessengerAdapterConfig` fields are now
optional
(the factory still falls back to `FACEBOOK_*` env vars), and `logger` /
`userName` live on `MessengerAdapterConfig` directly. The factory
signature
is now `createMessengerAdapter(config?: MessengerAdapterConfig)`.
- `@chat-adapter/web`: renamed `WebAdapterOptions` to
`WebAdapterConfig`; the
old name is exported as a deprecated alias.
- `@chat-adapter/whatsapp`: every field on `WhatsAppAdapterConfig` is
optional
(the factory still falls back to `WHATSAPP_*` env vars).
`createWhatsAppAdapter`
is now typed `(config?: WhatsAppAdapterConfig) => WhatsAppAdapter`.
- `@chat-adapter/state-memory`: added an empty
`MemoryStateAdapterOptions`
type so the package matches every other state adapter;
`createMemoryState`
now accepts an optional argument of that type.
- `@chat-adapter/state-ioredis`, `@chat-adapter/state-redis`,
`@chat-adapter/state-pg`: the URL- and client-based option shapes were
split
into named interfaces (`*StateAdapterUrlOptions` /
`*StateAdapterClientOptions`) and unified under `*StateAdapterOptions`.
The
factories now take the union type directly. Old names —
`RedisStateClientOptions`,
`CreateRedisStateOptions`, `PostgresStateClientOptions`,
`CreatePostgresStateOptions`, `IoRedisStateClientOptions` — are kept as
deprecated aliases.
- 0f0c203: fix(slack): prefer `webhookVerifier` over `signingSecret` and
`SLACK_SIGNING_SECRET`
When a `webhookVerifier` is configured, it now takes precedence over
both the
`signingSecret` config field and the `SLACK_SIGNING_SECRET` env var.
Previously,
a configured `signingSecret` (or env var) would shadow the verifier.
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [add2730]
- Updated dependencies [b75eedb]
- chat@4.29.0
- @chat-adapter/shared@4.29.0
## @chat-adapter/teams@4.29.0
### Minor Changes
- 2ffed48: Adapter internals are now `protected` rather than `private`,
so consumers can subclass an adapter to override or extend its behavior
(e.g. handling additional Telegram update types by overriding
`processUpdate`).
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [add2730]
- Updated dependencies [b75eedb]
- chat@4.29.0
- @chat-adapter/shared@4.29.0
## @chat-adapter/telegram@4.29.0
### Minor Changes
- add2730: support typed Telegram attachment uploads
- 2ffed48: Adapter internals are now `protected` rather than `private`,
so consumers can subclass an adapter to override or extend its behavior
(e.g. handling additional Telegram update types by overriding
`processUpdate`).
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- 711babe: Handle `video_note` (round video messages) in
`extractAttachments`. Previously these messages were silently dropped;
now they are returned as `video` attachments with `width`/`height` set
to the clip's `length`.
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [add2730]
- Updated dependencies [b75eedb]
- chat@4.29.0
- @chat-adapter/shared@4.29.0
## @chat-adapter/web@4.29.0
### Minor Changes
- 2ffed48: Adapter internals are now `protected` rather than `private`,
so consumers can subclass an adapter to override or extend its behavior
(e.g. handling additional Telegram update types by overriding
`processUpdate`).
- 716e934: Add first-class Vue and Svelte support via new subpath
exports `@chat-adapter/web/vue` and `@chat-adapter/web/svelte`. Each
exports a `useChat()` factory preconfigured with `DefaultChatTransport`,
returning a framework-reactive `Chat` instance from `@ai-sdk/vue` /
`@ai-sdk/svelte` respectively. Note: unlike the React subpath which
wraps `@ai-sdk/react`'s `useChat` hook and returns destructurable
helpers, the Vue and Svelte wrappers return a `Chat` class instance —
access `chat.messages`, `chat.sendMessage()`, `chat.status`, and
`chat.stop()` directly on the object.
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- 06fb8e5: Align package shapes with the new `konsistent` conventions.
All changes are
backwards-compatible — previous type names are kept as deprecated
aliases.
- `@chat-adapter/gchat`, `@chat-adapter/slack`: moved `*AdapterConfig`
(and
related sub-types) into a `./types` module; the public re-exports from
`index.ts` are unchanged.
- `@chat-adapter/slack`: `createSlackAdapter` now accepts
`SlackAdapterConfig`
directly instead of `Partial<SlackAdapterConfig>`. Every field on the
config
was already optional, so no call sites need to change.
- `@chat-adapter/messenger`: `MessengerAdapterConfig` fields are now
optional
(the factory still falls back to `FACEBOOK_*` env vars), and `logger` /
`userName` live on `MessengerAdapterConfig` directly. The factory
signature
is now `createMessengerAdapter(config?: MessengerAdapterConfig)`.
- `@chat-adapter/web`: renamed `WebAdapterOptions` to
`WebAdapterConfig`; the
old name is exported as a deprecated alias.
- `@chat-adapter/whatsapp`: every field on `WhatsAppAdapterConfig` is
optional
(the factory still falls back to `WHATSAPP_*` env vars).
`createWhatsAppAdapter`
is now typed `(config?: WhatsAppAdapterConfig) => WhatsAppAdapter`.
- `@chat-adapter/state-memory`: added an empty
`MemoryStateAdapterOptions`
type so the package matches every other state adapter;
`createMemoryState`
now accepts an optional argument of that type.
- `@chat-adapter/state-ioredis`, `@chat-adapter/state-redis`,
`@chat-adapter/state-pg`: the URL- and client-based option shapes were
split
into named interfaces (`*StateAdapterUrlOptions` /
`*StateAdapterClientOptions`) and unified under `*StateAdapterOptions`.
The
factories now take the union type directly. Old names —
`RedisStateClientOptions`,
`CreateRedisStateOptions`, `PostgresStateClientOptions`,
`CreatePostgresStateOptions`, `IoRedisStateClientOptions` — are kept as
deprecated aliases.
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [add2730]
- Updated dependencies [b75eedb]
- chat@4.29.0
- @chat-adapter/shared@4.29.0
## @chat-adapter/whatsapp@4.29.0
### Minor Changes
- 2ffed48: Adapter internals are now `protected` rather than `private`,
so consumers can subclass an adapter to override or extend its behavior
(e.g. handling additional Telegram update types by overriding
`processUpdate`).
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- 06fb8e5: Align package shapes with the new `konsistent` conventions.
All changes are
backwards-compatible — previous type names are kept as deprecated
aliases.
- `@chat-adapter/gchat`, `@chat-adapter/slack`: moved `*AdapterConfig`
(and
related sub-types) into a `./types` module; the public re-exports from
`index.ts` are unchanged.
- `@chat-adapter/slack`: `createSlackAdapter` now accepts
`SlackAdapterConfig`
directly instead of `Partial<SlackAdapterConfig>`. Every field on the
config
was already optional, so no call sites need to change.
- `@chat-adapter/messenger`: `MessengerAdapterConfig` fields are now
optional
(the factory still falls back to `FACEBOOK_*` env vars), and `logger` /
`userName` live on `MessengerAdapterConfig` directly. The factory
signature
is now `createMessengerAdapter(config?: MessengerAdapterConfig)`.
- `@chat-adapter/web`: renamed `WebAdapterOptions` to
`WebAdapterConfig`; the
old name is exported as a deprecated alias.
- `@chat-adapter/whatsapp`: every field on `WhatsAppAdapterConfig` is
optional
(the factory still falls back to `WHATSAPP_*` env vars).
`createWhatsAppAdapter`
is now typed `(config?: WhatsAppAdapterConfig) => WhatsAppAdapter`.
- `@chat-adapter/state-memory`: added an empty
`MemoryStateAdapterOptions`
type so the package matches every other state adapter;
`createMemoryState`
now accepts an optional argument of that type.
- `@chat-adapter/state-ioredis`, `@chat-adapter/state-redis`,
`@chat-adapter/state-pg`: the URL- and client-based option shapes were
split
into named interfaces (`*StateAdapterUrlOptions` /
`*StateAdapterClientOptions`) and unified under `*StateAdapterOptions`.
The
factories now take the union type directly. Old names —
`RedisStateClientOptions`,
`CreateRedisStateOptions`, `PostgresStateClientOptions`,
`CreatePostgresStateOptions`, `IoRedisStateClientOptions` — are kept as
deprecated aliases.
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [add2730]
- Updated dependencies [b75eedb]
- chat@4.29.0
- @chat-adapter/shared@4.29.0
## chat@4.29.0
### Minor Changes
- ac8a207: Add `chat/ai` subpath as the home for AI utilities, including
`createChatTools` for the Vercel AI SDK and `toAiMessages` for
converting chat history into AI SDK prompts.
`createChatTools` exposes Chat SDK operations as ready-to-use AI SDK
tools so an agent can read messages, post replies, send DMs, react,
edit, delete, and manage thread subscriptions across every adapter the
supplied `Chat` instance has registered. Write operations require user
approval by default and can be toggled globally or per-tool via
`requireApproval`. Three presets (`reader`, `messenger`, `moderator`)
scope the toolset, and tools can also be cherry-picked from the same
subpath.
`toAiMessages` (and the `AiMessage` / `AiMessagePart` /
`ToAiMessagesOptions` types) now ship from `chat/ai` alongside the tools
— keeping the optional `ai` and `zod` peer dependencies out of bundles
that don't use them. The previous `chat` re-exports continue to work,
but are marked `@deprecated` so editors surface a hint pointing at
`chat/ai`; existing code keeps compiling, and migrating is a single
import-path change.
- b75eedb: add burst concurrency strategy
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
## @chat-adapter/state-ioredis@4.29.0
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- 06fb8e5: Align package shapes with the new `konsistent` conventions.
All changes are
backwards-compatible — previous type names are kept as deprecated
aliases.
- `@chat-adapter/gchat`, `@chat-adapter/slack`: moved `*AdapterConfig`
(and
related sub-types) into a `./types` module; the public re-exports from
`index.ts` are unchanged.
- `@chat-adapter/slack`: `createSlackAdapter` now accepts
`SlackAdapterConfig`
directly instead of `Partial<SlackAdapterConfig>`. Every field on the
config
was already optional, so no call sites need to change.
- `@chat-adapter/messenger`: `MessengerAdapterConfig` fields are now
optional
(the factory still falls back to `FACEBOOK_*` env vars), and `logger` /
`userName` live on `MessengerAdapterConfig` directly. The factory
signature
is now `createMessengerAdapter(config?: MessengerAdapterConfig)`.
- `@chat-adapter/web`: renamed `WebAdapterOptions` to
`WebAdapterConfig`; the
old name is exported as a deprecated alias.
- `@chat-adapter/whatsapp`: every field on `WhatsAppAdapterConfig` is
optional
(the factory still falls back to `WHATSAPP_*` env vars).
`createWhatsAppAdapter`
is now typed `(config?: WhatsAppAdapterConfig) => WhatsAppAdapter`.
- `@chat-adapter/state-memory`: added an empty
`MemoryStateAdapterOptions`
type so the package matches every other state adapter;
`createMemoryState`
now accepts an optional argument of that type.
- `@chat-adapter/state-ioredis`, `@chat-adapter/state-redis`,
`@chat-adapter/state-pg`: the URL- and client-based option shapes were
split
into named interfaces (`*StateAdapterUrlOptions` /
`*StateAdapterClientOptions`) and unified under `*StateAdapterOptions`.
The
factories now take the union type directly. Old names —
`RedisStateClientOptions`,
`CreateRedisStateOptions`, `PostgresStateClientOptions`,
`CreatePostgresStateOptions`, `IoRedisStateClientOptions` — are kept as
deprecated aliases.
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [b75eedb]
- chat@4.29.0
## @chat-adapter/state-memory@4.29.0
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- 06fb8e5: Align package shapes with the new `konsistent` conventions.
All changes are
backwards-compatible — previous type names are kept as deprecated
aliases.
- `@chat-adapter/gchat`, `@chat-adapter/slack`: moved `*AdapterConfig`
(and
related sub-types) into a `./types` module; the public re-exports from
`index.ts` are unchanged.
- `@chat-adapter/slack`: `createSlackAdapter` now accepts
`SlackAdapterConfig`
directly instead of `Partial<SlackAdapterConfig>`. Every field on the
config
was already optional, so no call sites need to change.
- `@chat-adapter/messenger`: `MessengerAdapterConfig` fields are now
optional
(the factory still falls back to `FACEBOOK_*` env vars), and `logger` /
`userName` live on `MessengerAdapterConfig` directly. The factory
signature
is now `createMessengerAdapter(config?: MessengerAdapterConfig)`.
- `@chat-adapter/web`: renamed `WebAdapterOptions` to
`WebAdapterConfig`; the
old name is exported as a deprecated alias.
- `@chat-adapter/whatsapp`: every field on `WhatsAppAdapterConfig` is
optional
(the factory still falls back to `WHATSAPP_*` env vars).
`createWhatsAppAdapter`
is now typed `(config?: WhatsAppAdapterConfig) => WhatsAppAdapter`.
- `@chat-adapter/state-memory`: added an empty
`MemoryStateAdapterOptions`
type so the package matches every other state adapter;
`createMemoryState`
now accepts an optional argument of that type.
- `@chat-adapter/state-ioredis`, `@chat-adapter/state-redis`,
`@chat-adapter/state-pg`: the URL- and client-based option shapes were
split
into named interfaces (`*StateAdapterUrlOptions` /
`*StateAdapterClientOptions`) and unified under `*StateAdapterOptions`.
The
factories now take the union type directly. Old names —
`RedisStateClientOptions`,
`CreateRedisStateOptions`, `PostgresStateClientOptions`,
`CreatePostgresStateOptions`, `IoRedisStateClientOptions` — are kept as
deprecated aliases.
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [b75eedb]
- chat@4.29.0
## @chat-adapter/state-pg@4.29.0
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- 06fb8e5: Align package shapes with the new `konsistent` conventions.
All changes are
backwards-compatible — previous type names are kept as deprecated
aliases.
- `@chat-adapter/gchat`, `@chat-adapter/slack`: moved `*AdapterConfig`
(and
related sub-types) into a `./types` module; the public re-exports from
`index.ts` are unchanged.
- `@chat-adapter/slack`: `createSlackAdapter` now accepts
`SlackAdapterConfig`
directly instead of `Partial<SlackAdapterConfig>`. Every field on the
config
was already optional, so no call sites need to change.
- `@chat-adapter/messenger`: `MessengerAdapterConfig` fields are now
optional
(the factory still falls back to `FACEBOOK_*` env vars), and `logger` /
`userName` live on `MessengerAdapterConfig` directly. The factory
signature
is now `createMessengerAdapter(config?: MessengerAdapterConfig)`.
- `@chat-adapter/web`: renamed `WebAdapterOptions` to
`WebAdapterConfig`; the
old name is exported as a deprecated alias.
- `@chat-adapter/whatsapp`: every field on `WhatsAppAdapterConfig` is
optional
(the factory still falls back to `WHATSAPP_*` env vars).
`createWhatsAppAdapter`
is now typed `(config?: WhatsAppAdapterConfig) => WhatsAppAdapter`.
- `@chat-adapter/state-memory`: added an empty
`MemoryStateAdapterOptions`
type so the package matches every other state adapter;
`createMemoryState`
now accepts an optional argument of that type.
- `@chat-adapter/state-ioredis`, `@chat-adapter/state-redis`,
`@chat-adapter/state-pg`: the URL- and client-based option shapes were
split
into named interfaces (`*StateAdapterUrlOptions` /
`*StateAdapterClientOptions`) and unified under `*StateAdapterOptions`.
The
factories now take the union type directly. Old names —
`RedisStateClientOptions`,
`CreateRedisStateOptions`, `PostgresStateClientOptions`,
`CreatePostgresStateOptions`, `IoRedisStateClientOptions` — are kept as
deprecated aliases.
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [b75eedb]
- chat@4.29.0
## @chat-adapter/state-redis@4.29.0
### Patch Changes
- e60bc8c: chore: set supported Node versions in engines
- 06fb8e5: Align package shapes with the new `konsistent` conventions.
All changes are
backwards-compatible — previous type names are kept as deprecated
aliases.
- `@chat-adapter/gchat`, `@chat-adapter/slack`: moved `*AdapterConfig`
(and
related sub-types) into a `./types` module; the public re-exports from
`index.ts` are unchanged.
- `@chat-adapter/slack`: `createSlackAdapter` now accepts
`SlackAdapterConfig`
directly instead of `Partial<SlackAdapterConfig>`. Every field on the
config
was already optional, so no call sites need to change.
- `@chat-adapter/messenger`: `MessengerAdapterConfig` fields are now
optional
(the factory still falls back to `FACEBOOK_*` env vars), and `logger` /
`userName` live on `MessengerAdapterConfig` directly. The factory
signature
is now `createMessengerAdapter(config?: MessengerAdapterConfig)`.
- `@chat-adapter/web`: renamed `WebAdapterOptions` to
`WebAdapterConfig`; the
old name is exported as a deprecated alias.
- `@chat-adapter/whatsapp`: every field on `WhatsAppAdapterConfig` is
optional
(the factory still falls back to `WHATSAPP_*` env vars).
`createWhatsAppAdapter`
is now typed `(config?: WhatsAppAdapterConfig) => WhatsAppAdapter`.
- `@chat-adapter/state-memory`: added an empty
`MemoryStateAdapterOptions`
type so the package matches every other state adapter;
`createMemoryState`
now accepts an optional argument of that type.
- `@chat-adapter/state-ioredis`, `@chat-adapter/state-redis`,
`@chat-adapter/state-pg`: the URL- and client-based option shapes were
split
into named interfaces (`*StateAdapterUrlOptions` /
`*StateAdapterClientOptions`) and unified under `*StateAdapterOptions`.
The
factories now take the union type directly. Old names —
`RedisStateClientOptions`,
`CreateRedisStateOptions`, `PostgresStateClientOptions`,
`CreatePostgresStateOptions`, `IoRedisStateClientOptions` — are kept as
deprecated aliases.
- Updated dependencies [ac8a207]
- Updated dependencies [e60bc8c]
- Updated dependencies [b75eedb]
- chat@4.29.0
## @chat-adapter/tests@4.29.0
### Patch Changes
- 0adf3ad: Add `@chat-adapter/tests` — Vitest factories, matchers, and
setup utilities for Chat SDK adapter and bot authors.
- **Factories**: `createMockAdapter`, `createMockChatInstance`,
`createMockState` (with working in-memory
subscriptions/locks/KV/queues), `createTestMessage`,
`mockLogger`/`createMockLogger`.
- **Matchers**: `toHavePosted(threadId, textPattern?)`,
`toHaveDispatched(handler)`, `toBeSubscribedTo(threadId)`.
- **Setup file**: `@chat-adapter/tests/setup` registers all matchers via
`expect.extend` — drop into `vitest.config.ts` `setupFiles`.
`chat` and `vitest` are peer dependencies. Adapter-specific helpers
(e.g. signed Slack webhook builders) belong in each adapter's own
`/testing` subpath, not in this kit.
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
## Summary
Introduces a dedicated `chat/ai` subpath as the home for every Vercel AI
SDK helper that ships with Chat SDK. Importing from this subpath keeps
the optional `ai` and `zod` peer dependencies out of bundles that don't
use them.
### What's new
- **`createChatTools`** — exposes Chat SDK operations as ready-to-use AI
SDK tools so an agent can read, post, react, edit, delete, and manage
thread subscriptions across every adapter the supplied `Chat` instance
has registered.
- Write operations require user approval by default (`requireApproval:
true`); toggle globally or per-tool.
- Three presets — `reader`, `messenger`, `moderator` — scope the
toolset.
- Individual tools can also be cherry-picked (`import { postMessage,
addReaction } from "chat/ai"`).
- **`toAiMessages`** (and the `Ai*` / `ToAiMessagesOptions` types) now
live alongside the tools at `chat/ai`. The previous `chat` re-exports
continue to work, but are flagged `@deprecated` with an editor hint
pointing to the new home — migration is a one-line import change.
- **Docs** — new `/docs/ai` section between Usage and Adapters in the
sidebar:
- `/docs/ai` — Overview
- `/docs/ai/ai-sdk-tools` — `createChatTools` guide
- `/docs/ai/to-ai-messages` — `toAiMessages` reference
- `/docs/ai/types` — Reference for every type exported from `chat/ai`
- **Example app** — `examples/nextjs-chat` now demos the new surface via
a "Run Agent Demo" button on the welcome card and a free-form `/agent
<prompt>` slash command (streaming, with a placeholder so users get
immediate feedback in channel contexts where Slack's typing-status API
is a no-op).
### Future plans
`createChatTools` currently exposes the cross-adapter Chat SDK surface
only. A natural follow-up is to also support **platform-specific tools**
— e.g. expose Slack-only `pin`/`unpin`, Discord-only thread archiving,
GitHub-only issue commenting, etc., so users can further extend what
their agent can do without dropping back to raw adapter calls. The shape
would likely be additional opt-in factories under `chat/ai` (or
per-adapter subpaths like `@chat-adapter/slack/ai`) that return tools
layered on top of the platform-specific adapter clients, while keeping
the cross-platform `createChatTools` API as the lowest common
denominator.
### Coverage
- `createChatTools` orchestrator: 100% statements / 94.7% branches.
- Every tool factory's `execute()` is exercised end-to-end (29 tests in
`index.test.ts`).
- `toAiMessages` keeps its existing 35-test suite covering role mapping,
attachment handling, links, transforms, and unsupported-attachment
fallbacks.
- Tools folder overall: 99.0% statements / 86.1% branches / 97.4%
functions / 98.9% lines.
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
Co-authored-by: dancer <josh@afterima.ge>
## summary
adds an opt-in `burst` concurrency strategy for #414
when a thread is idle, the first message waits for `debounceMs`,
messages that arrive during that window are queued, and the handler runs
once with the latest message plus earlier burst messages in
`context.skipped`
after the handler finishes, messages that arrived while it was running
are drained like `queue`, so the latest queued message is processed with
earlier queued messages in `context.skipped`
keeps existing `drop`, `queue`, `debounce`, and `concurrent` behavior
unchanged
updates docs to cover `burst`, explain when to choose it over
`debounce`, and document the related `MessageContext` behavior
## summary
clarifies that registered `onDirectMessage` handlers take precedence for
incoming DM messages before subscribed-message, mention, and pattern
routing
updates the direct messages, event handling, thread subscription, and
API docs so they match the current runtime behavior
adds `onDirectMessage` to the Chat API docs
fixes#432
* add .nvmrc file
* follow up
* make support of Node >= 20 explicit
* update default Node version for contributing to the repo to 24
* run build-and-test CI job for both Node 20 and 24
* add changeset for package.json change
* [messenger] add messenger (meta) platform adapter to chat sdk
- Webhook handling with HMAC-SHA256 signature verification
- Generic and Button template support for cards
- Postback, reaction, delivery/read confirmation handling
- Message caching for fetchMessages (Messenger has no history API)
- Replay tests and ~98% code coverage
Co-authored-by: Dimitar K. Nikolov <mitkodkn@users.noreply.github.com>
Co-authored-by: Ben Sabic <27636870+bensabic@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* Fix: The `@chat-adapter/messenger` package version is `4.15.0` while all other packages in the Changesets fixed version group are at `4.27.0`, breaking the fixed versioning contract.
This commit fixes the issue reported at packages/adapter-messenger/package.json:3
**Bug explanation:**
The repository uses Changesets with a `"fixed"` configuration: `[["chat", "@chat-adapter/*"]]`. This means all packages matching these patterns must always share the same version number. Every package in the group (`chat`, `@chat-adapter/discord`, `@chat-adapter/gchat`, `@chat-adapter/github`, `@chat-adapter/linear`, `@chat-adapter/shared`, `@chat-adapter/slack`, `@chat-adapter/teams`, `@chat-adapter/telegram`, `@chat-adapter/web`, `@chat-adapter/whatsapp`, and the state packages) is at version `4.27.0`, except `@chat-adapter/messenger` which is at `4.15.0`.
This is likely because the messenger adapter was newly added to the monorepo (copied from a template or created fresh) and its version was never aligned with the rest of the fixed group. This mismatch will cause problems with the Changesets release workflow — when Changesets tries to bump versions for the fixed group, it may produce inconsistent or errored releases because one package is 12 minor versions behind the others.
**Fix explanation:**
Changed `"version": "4.15.0"` to `"version": "4.27.0"` in `packages/adapter-messenger/package.json` to align it with all other packages in the fixed version group.
Co-authored-by: Vercel <vercel[bot]@users.noreply.github.com>
Co-authored-by: visyat <vishal.yathish@gmail.com>
* Fix: Messenger adapter env var guard only checks `FACEBOOK_APP_SECRET` but `createMessengerAdapter` requires all three env vars, causing a `ValidationError` crash at Next.js build time when only `FACEBOOK_APP_SECRET` is set.
This commit fixes the issue reported at examples/nextjs-chat/src/lib/adapters.ts:154
**Bug Analysis:**
The build failure is confirmed in the Vercel build log with:
```
Error [ValidationError]: pageAccessToken is required. Set FACEBOOK_PAGE_ACCESS_TOKEN or provide it in config.
```
The root cause is in `examples/nextjs-chat/src/lib/adapters.ts` at line ~154. The messenger adapter guard only checks for `FACEBOOK_APP_SECRET`:
```typescript
if (process.env.FACEBOOK_APP_SECRET) {
```
However, `createMessengerAdapter` (in `packages/adapter-messenger/src/index.ts`) validates and throws `ValidationError` for each of three required env vars: `FACEBOOK_APP_SECRET`, `FACEBOOK_PAGE_ACCESS_TOKEN`, and `FACEBOOK_VERIFY_TOKEN`. When only `FACEBOOK_APP_SECRET` is set in the Vercel project environment, the guard passes, `createMessengerAdapter` is called, and it throws a `ValidationError` for the missing `FACEBOOK_PAGE_ACCESS_TOKEN`. Since this code runs at module evaluation time during the Next.js build's "Collecting page data" phase, the uncaught error crashes the entire build.
This is inconsistent with other adapters in the same file. For example, the WhatsApp adapter checks both `WHATSAPP_ACCESS_TOKEN` and `WHATSAPP_PHONE_NUMBER_ID`, and the gchat/github/linear/whatsapp adapters all wrap creation in try-catch blocks.
**Fix:**
1. Updated the env var guard to check all three required environment variables (`FACEBOOK_APP_SECRET`, `FACEBOOK_PAGE_ACCESS_TOKEN`, and `FACEBOOK_VERIFY_TOKEN`) before attempting to create the adapter.
2. Wrapped the `createMessengerAdapter` call in a try-catch block (matching the pattern used by gchat, github, linear, and whatsapp adapters) so that any unexpected validation errors are caught and logged as warnings instead of crashing the build.
Co-authored-by: Vercel <vercel[bot]@users.noreply.github.com>
Co-authored-by: visyat <vishal.yathish@gmail.com>
---------
Co-authored-by: Dimitar K. Nikolov <mitkodkn@users.noreply.github.com>
Co-authored-by: Ben Sabic <27636870+bensabic@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com>
Co-authored-by: Vercel <vercel[bot]@users.noreply.github.com>
* 1
* w
* 3f
* x
* ln
* gh
* sl
* t1
* u
* t2
* t3
* t4
* t5
* d
* d2
* cs
* fx
* cl
* docs: clean up subject + .client docs and restructure nav
- subject.mdx: simplify prose, drop redundant platform lists, link to MessageSubject API and getAdapter
- api/message.mdx: add MessageSubject TypeTable
- api/chat.mdx: expand getAdapter with Direct client access content
- adapters.mdx: add Parent subject and Native client rows to feature matrix
- usage.mdx: mention .client under Accessing adapters
- adapter-github/-linear READMEs: add Direct API client section
- meta.json: split Features into Messaging + Interactivity, move error-handling to Usage
- title case across messaging-cluster page titles
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
* feat(chat): expose awaitable Promise from processMessage
Return the inner task as Promise<void> instead of void so streaming
adapters can await full handler completion and surface user-handler
rejections at the wire level. waitUntil semantics for existing webhook
adapters are unchanged — the SDK still tracks the work with errors
swallowed (and logged) so platforms don't retry on handler bugs.
Required by @chat-adapter/web, whose response body is the user
handler's stream.
* feat(adapter-web): add @chat-adapter/web package
A new platform adapter that lets a chat-sdk bot serve a browser chat
UI alongside Slack/Teams/Discord/etc. without writing any client-side
glue. Speaks the AI SDK UI message stream protocol, so @ai-sdk/react's
useChat and the ai-elements component library work out of the box.
- `@chat-adapter/web` — server: createWebAdapter({ userName, getUser })
- `@chat-adapter/web/react` — client: useChat() preconfigured with
DefaultChatTransport against /api/chat (override via `api`)
Defaults that matter for v1:
- `isDM: true` — every web message routes through onDirectMessage
- `persistMessageHistory: true` — chat-sdk caches each turn in the
configured state adapter so handlers can read prior context via
thread.messages / channel.messages (no platform history API exists)
- channelId === threadId — web has no separate channel concept; this
prevents cross-conversation bleed when a single user has multiple
useChat sessions
- Native `adapter.stream` implementation pumps text-deltas straight
onto the SSE response — no post+edit fallback
Out of scope for v1: cards/JSX rendering, reactions, modals, file
uploads, edit/delete, multi-tab proactive push.
* feat(example-nextjs-chat): wire up web adapter and add /chat page
- Register the web adapter in lib/adapters.ts with a demo getUser
(single shared identity — replace with NextAuth/Clerk/cookie auth
in production)
- Expose POST /api/chat backed by bot.webhooks.web (using next/after
for waitUntil)
- Add a minimal /chat page using @chat-adapter/web/react's useChat —
same bot.onDirectMessage handler that powers Slack now powers the
browser too
Bumps `ai` to ^6.0.174 to align with @ai-sdk/react@^3 (avoids dual
provider-utils versions in the workspace).
* docs: list @chat-adapter/web in registry
- Add an entry to adapters.json so the package shows up on /adapters
- Add a globe SVG to lib/logos.tsx and wire it into the icon map
- Mention the new adapter in docs/adapters.mdx
* feat(adapter-web): tighten request handling and message construction
- Reject user ids containing ':' with HTTP 400 — the character would
corrupt the thread-id round-trip through decodeThreadId
- Skip emitting text-start/text-end in postMessage when the resolved
text is empty so useChat doesn't render blank assistant bubbles
- Derive the parseMessage author from raw.role so rehydrated assistant
messages report the bot identity instead of "unknown"
- Drop the duplicate handler-error log; chat.processMessage already
logs at ERROR level
- Document the actual persistMessageHistory default (true) and the
state-cache rationale; promote the fetchMessages no-op rationale
into its JSDoc
* test(adapter-web): add direct coverage for stream()
- Aborting request.signal mid-stream short-circuits the iterator and
still writes text-end via the finally block
- Non-text StreamChunks (task_update, plan_update) are dropped without
emitting any delta
- The SentMessage returned from thread.post matches the id used in
text-start / text-end events
* docs(adapter-web): expand README into the full adapter docs page
The docs site renders each adapter's README, so flesh out
@chat-adapter/web to match the depth of @chat-adapter/slack:
authentication boundary, threading semantics, streaming,
persistence, React hook reference, configuration table,
feature matrix, and troubleshooting.
* docs(adapter-web): drop unsupported provider import from streaming example
* fix(adapter-web): validate conversationId for reserved colon character
* fix(example): show error state in web chat demo
* fix(example): add thinking indicator to web chat demo
* feat(example): redesign web chat demo with tailwind
* chore: remove redundant changeset
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
Co-authored-by: dancer <josh@afterima.ge>
* feat(chat): add Transcripts API and rename per-thread cache to threadHistory
Introduce `bot.transcripts` for cross-platform per-user message persistence.
When `ChatConfig.transcripts` and `ChatConfig.identity` are configured, every
inbound message has its `userKey` resolved during dispatch and the API exposes
`append` / `list` / `count` / `delete` keyed by that user. Backed by the
existing `StateAdapter.appendToList` primitive — every built-in state adapter
supports it with no contract changes.
Rename the existing per-thread history cache from `messageHistory` to
`threadHistory` (with backwards compat for `ChatConfig.messageHistory` and
`Adapter.persistMessageHistory`) so the two persistence layers don't share a
"messages" name. The state-adapter storage key prefix is unchanged so existing
data isn't orphaned.
`delete()` writes a tombstone via `appendToList(key, _, { maxLength: 1 })`
rather than `state.delete(key)`, because `state.delete` only addresses the
k/v namespace on every non-memory state adapter — `list()` and `count()`
filter the tombstone out so the API contract is preserved.
* docs(chat): cover Transcripts API and Conversation history
Add a Features-style "Conversation history" guide (`/docs/conversation-history`)
walking through identity resolution, the LLM-context append/list pattern,
filtering, and per-user deletion for DSR flows.
Add an API reference page at `/docs/api/transcripts` with `<TypeTable>` blocks
for `ChatConfig.transcripts`, `ChatConfig.identity`, every method on
`bot.transcripts`, and the `TranscriptEntry` shape.
Wire both into the corresponding `meta.json` files.
* example(nextjs-chat): wire Transcripts API into the AI mode handler
Replace the brittle `threadState.history` shim with `bot.transcripts.list({ ..., threadId, limit })` as the fallback context source for platforms without
`fetchMessages` (Telegram, WhatsApp). Drop the `history` field from
`ThreadState` accordingly.
Add a hardcoded `TEST_USER_KEY = "test-user"` so the API can be exercised
without juggling real user identities, plus "Show Transcripts" and
"Clear Transcripts" buttons in the welcome card so the store can be
inspected and reset from chat.
* fix(chat): tighten Transcripts API public surface and wiring
Polish on top of the Transcripts API + threadHistory rename, addressing
review concerns before merge.
Public surface (`types.ts`, `index.ts`):
- Expose `transcripts` on the `ChatInstance` interface so callers typed
against the public interface can reach `bot.transcripts`.
- Promote the `count` argument to a named `CountQuery` interface,
matching `DeleteTarget` / `ListQuery`. Exported from `index.ts`.
- Document on `TranscriptsApi.list()` that pagination is intentionally
out-of-scope — the store keeps at most `maxPerUser` entries per user.
- Reconcile the `TranscriptEntry.id` JSDoc with the implementation:
UUID assigned at append time, returned in append order, not
lexicographically sortable; use `timestamp` for cross-store ordering.
Wiring (`chat.ts`):
- Include `threadId` in the identity-resolver failure log context so
operators can correlate failures with the source thread.
Stale-reference sweep:
- Replace lingering "Messages API" / `chat.messages` /
`messages.storeFormatted` strings in shipped JSDoc with the new
`transcripts` names (these ride into `.d.ts` and are user-visible).
- Fix the dead `[Messages API](./messages.ts)` link in the existing
thread-history-rename changeset.
* test(chat): cover dual-read precedence, resolver edges, concurrent ops
Fill gaps in the Transcripts API + threadHistory rename test suite:
`chat.test.ts` (persistThreadHistory block):
- top-level `config.messageHistory` (deprecated alias) flows through
to the per-thread cache when `threadHistory` is unset
- `threadHistory` takes precedence over `messageHistory` when both are
set — pinned by asserting `appendToList` receives the new config's
`maxLength` / `ttlMs`
- both `persistThreadHistory` and `persistMessageHistory` set on the
adapter still triggers persistence
`transcripts-wiring.test.ts`:
- sync resolver returning a plain string populates `message.userKey`
- resolver returning `""` is treated as no userKey (truthy check at
the dispatch hook would silently flip if a future change moved to
`!== undefined`)
`transcripts.test.ts`:
- concurrent append/delete/append interleave preserves invariants:
`count()` and `list()` agree (no tombstone leak), no pre-delete
entry survives, and the post-delete result is bounded by the two
concurrent appends
* docs(chat): use named types in Transcripts API reference
- `formatted` rows in the AppendInput / TranscriptEntry TypeTables
now render `FormattedContent | undefined` (the alias actually
exported from `chat`), instead of `Root | undefined` which would
force readers to pull the type from `mdast` directly.
- `count` signature uses the new `CountQuery` named type, with a
one-liner describing its single field.
* example(nextjs-chat): fix stale comment on transcripts demo handler
The action handler was relabelled to `transcripts` when it was wired
to `bot.transcripts.list`, but the leading comment still read
"Demonstrate fetchMessages and allMessages" from the previous
iteration. Update it to describe the transcripts demo.
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
* [chat] fix Slack streaming team ID for interactive payloads
* chore: downgrade changeset to patch
---------
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
* feat: add chat.getUser() for cross-platform user lookups
Add UserInfo type and optional getUser() method to the Adapter interface.
Implement on Slack (extends existing lookupUser with email/avatar),
Discord, Google Chat, GitHub, Linear, and Telegram adapters.
Add "Who Am I" button to the example app demonstrating the feature.
Update docs with getUser API reference and usage examples.
* fix(chat): improve getUser across slack and gchat adapters
- slack: return null from lookupUser on failure instead of fallback
object, removing the isBot === undefined sentinel in getUser
- slack: use image_192 instead of image_72 for better avatar quality
- gchat: cache avatarUrl from webhook sender payload
- gchat: return avatarUrl in getUser response
- gchat: fix tests to use current cache format with isBot field
- docs: document null return, fix example to use message.author
* chore: fix lint
* docs(chat): include Microsoft Teams in getUser supported adapters list
* feat(adapter-teams): add getUser() support (#404)
* feat(adapter-teams): add getUser() via Microsoft Graph API
- Cache aadObjectId from activity.from during webhook handling
- Implement getUser() using Graph GET /users/{user-id} endpoint
- Requires User.Read.All application permission
- Returns null gracefully when user hasn't interacted or Graph call fails
* docs: add getUser() section to Teams adapter README
* chore: apply ultracite formatting to adapter-teams getUser
* fix(chat): cover all 7 adapters in getUser inference and document per-platform constraints
---------
Co-authored-by: dancer <josh@afterima.ge>
* feat(chat): add initialOption and option_groups to ExternalSelect
* docs(modals): document ExternalSelect initialOption and option_groups, truncate group label to 75 chars
- Add scripts/sync-resources.ts (run via pnpm sync-resources) that reads apps/docs/resources-edge-config.json, fetches each guide's .md version over https with a timeout and size cap, writes templates.json, and regenerates the Available resources block in skills/chat/SKILL.md
- Migrate the Slack Next.js, Discord Nuxt, and Hono code-review guides from on-site MDX to Vercel KB and register them in the resources edge-config JSON alongside the existing external guides
- Remove /docs/guides MDX content, sidebar entries, top-level Guides nav entry, getting-started cards, and the dead /guides/ branch in the sitemap route now that all guides live externally and are surfaced on /resources
- Replace the homepage Guides/Templates section and the standalone Adapters pill section with a single two-column Resources + Adapters section (icons, headings, descriptions, outline buttons, divider), and drop the URL footer from ResourceCard on the Resources page
- Update skills/chat/SKILL.md to point at resources/guides and resources/templates.json and list the available guides and templates between marker comments that sync-resources rewrites
- Add tsx to knip's ignoreBinaries so npx tsx in the new script does not fail lint
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
Co-authored-by: dancer <josh@afterima.ge>
github-actions[bot]