* fix(github): accumulate stream before posting, log fallback edit errors
The GitHub adapter relied on chat-sdk's default fallbackStream which
posts a placeholder then edits it every 500ms. GitHub returns 422 on
these edits because body is empty during TTFT, and rapid edits risk
secondary rate limits.
Add stream() to GitHubAdapter that accumulates the full text before
posting once. Also log fallbackStream edit errors instead of silently
swallowing them.
* test: add tests for GitHub adapter stream() and fallbackStream logging
* style: format with biome
* refactor: use Logger instead of console.warn in fallbackStream
Plumb the Chat logger into ThreadImpl so fallbackStream uses the
structured logger instead of raw console.warn.
* test: simplify fallbackStream logging test
Reuse mockLogger from mock-adapter.ts and rely on createMockAdapter's
default editMessage mock instead of re-specifying the resolved value.
* test: use vi.mocked, drop redundant stream=undefined
* chore: add changeset
* refactor: extract accumulateStream utility, deduplicate GitHub and WhatsApp adapters
* Revert "refactor: extract accumulateStream utility, deduplicate GitHub and WhatsApp adapters"
This reverts commit 0a3ca3cc9a.
* feat: add LinkPreview to Message for URL and embedded message support
Add `links: LinkPreview[]` to `Message` so handlers can access URLs
shared in messages. Each LinkPreview contains the URL and optional
unfurl metadata (title, description, siteName, imageUrl).
On Slack, links are extracted from rich_text block elements (falling
back to <url> patterns in text). Links pointing to other Slack messages
(*.slack.com/archives/{channel}/p{ts}) include a `fetchMessage()`
callback that retrieves and parses the linked message.
`toAiMessages()` now appends link metadata to message content
automatically, labeling embedded message links distinctly so AI models
understand the context.
- Add LinkPreview interface to core types
- Add links field to Message, MessageData, SerializedMessage
- Extract links in Slack adapter (blocks + text fallback)
- Provide fetchMessage for Slack message URLs
- Set links: [] in all other adapters
- Include link metadata in toAiMessages() output
- Document LinkPreview in message API docs
- Document toAiMessages() in streaming and handling-events docs
- Add toAiMessages to API overview
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: remove redundant links: [] from adapters for backwards compatibility
The Message constructor already defaults links to [] when not provided,
so adapters that don't support link extraction don't need to pass it
explicitly. This makes the change backwards-compatible for third-party
adapters — they get an empty links array without any code changes.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: avoid polynomial regex in Slack link extraction
Replace `[^>|]+` pattern (which backtracks on `|`) with `[^>]+`
and a programmatic indexOf split. This prevents ReDoS on untrusted
message text.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add attachment support and mention tests to toAiMessages
toAiMessages now includes image and text-file attachments as multipart
content compatible with AI SDK's UserContent type:
- Images → ImagePart (via fetchData base64 or URL fallback)
- Text files (text/*, application/json, etc.) → FilePart
- Video/audio → warns via onUnsupportedAttachment callback
- Other file types → silently skipped
The function is now async to support fetchData() calls for inlining
attachment data as base64 data URIs. When fetchData fails, falls back
to the attachment URL.
Also adds mention rendering tests verifying that @mentions appear as
@name (not Slack's <@U123> syntax) in toAiMessages output, both in
plain messages and with links/includeNames enabled.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: make AiMessage types structurally compatible with AI SDK
Use a discriminated union (AiUserMessage | AiAssistantMessage) so
AiMessage[] is directly assignable to ModelMessage[] without casts.
Match DataContent type (string | Uint8Array | ArrayBuffer | Buffer)
for image/file parts to ensure structural compatibility.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(example): pass image attachments to AI via toAiMessages
The onNewMention handler was passing message.text directly to the AI
agent, dropping any image attachments. Now uses toAiMessages([message])
which includes images via fetchData as base64 inline data, enabling
the AI to actually see uploaded images.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: pass image data as Buffer, not data URI
The AI SDK expects DataContent (Buffer/Uint8Array/base64 string) for
image and file parts, not data URIs. Passing `data:image/png;base64,...`
caused "Could not process image" errors from the API. Now passes the
raw Buffer from fetchData() directly, with mediaType set separately.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: require fetchData for attachments, no URL fallback
Slack's url_private requires Bearer token auth that AI providers can't
provide. Remove URL fallback — attachments are only included when
fetchData() succeeds (which handles auth internally). Log errors
instead of silently falling through.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* debug: add temporary logging to toAiMessages image handling
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: use data URIs for image/file attachments in toAiMessages
The AI SDK's convertToLanguageModelV2DataContent parses data: URIs
to extract both the base64 content and media type. Raw base64 strings
lose the media type (returns mediaType: void 0), and raw Buffers may
not serialize correctly across network boundaries. Data URIs are the
most reliable format.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* debug: log fetched image size to diagnose API rejection
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* debug: log prompt structure to diagnose image rejection
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: use FilePart instead of ImagePart for image attachments
The AI SDK's ImagePart with data URI strings doesn't work correctly
through the AI Gateway. Use FilePart (type: "file") with data URI
in the data field instead — this matches the working pattern used by
other projects and handles image data correctly across all providers.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* debug: comprehensive logging at every decision point in toAiMessages
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* debug: log data prefix to verify content format
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* debug: log token capture and detect HTML responses from Slack file fetch
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: improve Slack file fetch error message and remove debug logging
When Slack returns an HTML login page instead of file data (typically
due to missing "files:read" OAuth scope), the error message now
explicitly tells the user what scope to add. Also removes all
temporary debug logging from toAiMessages and createAttachment.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Add transform support
* changeset
* address-feedback
* lint
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Initial marketplace draft
* Update language
* Add logos to cards
* Redesign cards
* Update adapter-card.tsx
* Update adapter-card.tsx
* Migrate marketplace to adapters
* Update meta.json
* Split adapters into new three groups
* Add iMessage
* Move adapter docs to READMEs
* Cleanup docs
* Add more logos, implement shadcn ui components
* Update adapters.json
* Add Streamdown
* Fetch vercel readmes from workspace
* Update readme-content.tsx
* Upgrade Streamdown
* Update global.css
* Update adapters.json
* Update adapters.json
* Add links to docs
* List upcoming official adapters
* Update adapters.json
* Fix adapters links
* Fix typo
* Misc fixes
* Update adapters.json
* Update adapters.json
* Migrate new info
* Update pnpm-lock.yaml
* Update adapter-card.tsx
* Add postgres to adapters page
* Update adapter-card.tsx
* Migrate postgres docs
* Add pg to valid README imports
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Move feature matrices from docs to package READMEs
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Remove packages tables from adapter/state docs
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Genericize adapter/state doc descriptions
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: improve adapters page accessibility and empty state handling
* Add custom adapter building section to SKILL.md
* Use currentColor for GitHub, Linear, and Memory icons
* Use GitHub API for README fetch, add heading to fallback state
Use the GitHub REST API instead of raw.githubusercontent.com to
automatically resolve the repo's default branch, so community
adapters using master or other branch names work correctly.
* Update adapters-grid.tsx
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Ben Sabic <bensabic@users.noreply.github.com>
* [chat] add Channel abstraction as first-class citizen alongside Thread
Introduces a Channel concept — the container that holds threads — enabling
channel-level operations, thread-to-channel navigation, and natural support
for threadless platforms (iMessage, WhatsApp, SMS).
Design:
- Postable base interface: shared by both Thread and Channel, providing id,
adapter, isDM, state/setState, messages (newest-first async iterator),
post, postEphemeral, startTyping, mentionUser. Enables polymorphic code
that works with either entity.
- Channel interface (extends Postable): adds name, threads() async iterator,
and fetchInfo(). ChannelImpl provides the concrete implementation with
backward message pagination, thread listing, posting, state management
(channel-state: key prefix), and workflow serialization (chat:Channel).
- Thread updates: Thread now extends Postable and gains a `channel` getter
(lazy-created, cached ChannelImpl) and a `messages` getter (newest-first
backward iterator) alongside the existing `allMessages` (oldest-first).
- Channel ID format: derived from thread IDs by dropping the thread part.
Default: first two colon-separated parts (slack:C123, gchat:spaces/ABC).
Adapters override via optional channelIdFromThreadId() method.
- Adapter interface additions (all optional): channelIdFromThreadId,
fetchChannelMessages, listThreads, fetchChannelInfo, postChannelMessage.
- Chat class: chat.channel(channelId) method creates a Channel by ID,
auto-inferring adapter from the prefix. Reviver handles chat:Channel.
- Slack adapter: implements all five channel methods using
conversations.history (vs conversations.replies for threads),
conversations.info, and chat.postMessage without thread_ts.
- Mock adapter: updated with all channel methods for testing.
- 32 new tests covering ChannelImpl, thread.channel, deriveChannelId,
and the backward messages iterator.
Usage:
// Navigate from thread to channel
const channel = thread.channel;
// Get a channel directly
const channel = chat.channel("slack:C123ABC");
// Iterate messages newest first
for await (const msg of channel.messages) { ... }
// List threads in a channel
for await (const t of channel.threads()) { ... }
// Post to channel top-level
await channel.post("Hello channel!");
TODO:
- Add replay tests for channel operations against recorded webhook data
- Implement channel methods in non-Slack adapters (GChat, Teams, Discord,
GitHub, Linear) — currently they fall back to the default/no-op behavior
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* channel-post-sample
* Better metadata
* Fix bug
* Fixes
* Other adapters
* Fix-gchat
* Fix-discord
* Fix-discord-threads
* Discord replay
* Teams tests and fix pre-existing failures
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
github-actions[bot]