Skip to content

Releases: slackapi/bolt-python

v1.26.0

07 Oct 02:17
@zimeg zimeg
v1.26.0
5f6196f
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.26.0 Latest
Latest

AI-Enabled Features: Loading States, Text Streaming, and Feedback Buttons

🍿 Preview

2025-10-06-loading-state-text-streaming-feedback.mov

📚 Changelog

⚡ Getting Started

Try the AI Agent Sample app to explore the AI-enabled features and existing Assistant helper:

# Create a new AI Agent app
$ slack create slack-ai-agent-app --template slack-samples/bolt-python-assistant-template
$ cd slack-ai-agent-app/

# Initialize Python Virtual Environment
$ python3 -m venv .venv
$ source .venv/bin/activate
$ pip install -r requirements.txt

# Add your OPENAI_API_KEY
$ export OPENAI_API_KEY=sk-proj-ahM...

# Run the local dev server
$ slack run

After the app starts, send a message to the "slack-ai-agent-app" bot for a unique response.

⌛ Loading States

Loading states allows you to not only set the status (e.g. "My app is typing...") but also sprinkle some personality by cycling through a collection of loading messages.

Bolt Assistant Class usage:

@assistant.user_message
def respond_in_assistant_thread(
    client: WebClient,
    context: BoltContext,
    get_thread_context: GetThreadContext,
    logger: Logger,
    payload: dict,
    say: Say,
    set_status: SetStatus,
):
    set_status(
        status="thinking...",
        loading_messages=[
            "Teaching the hamsters to type faster…",
            "Untangling the internet cables…",
            "Consulting the office goldfish…",
            "Polishing up the response just for you…",
            "Convincing the AI to stop overthinking…",
        ],
    )

Web Client SDK usage:

@app.message()
def handle_message(client, context, event, message):
    client.assistant_threads_setStatus(
        channel_id=channel_id,
        thread_ts=thread_ts,
        status="thinking...",
        loading_messages=[
            "Teaching the hamsters to type faster…",
            "Untangling the internet cables…",
            "Consulting the office goldfish…",
            "Polishing up the response just for you…",
            "Convincing the AI to stop overthinking…",
        ],
    )

    # Start a new message stream

🔮 Text Streaming Helper

The chat_stream() helper utility can be used to streamline calling the 3 text streaming methods:

# Start a new message stream
streamer = client.chat_stream(
    channel=channel_id,
    recipient_team_id=team_id,
    recipient_user_id=user_id,
    thread_ts=thread_ts,
)

# Loop over OpenAI response stream
# https://platform.openai.com/docs/api-reference/responses/create
for event in returned_message:
    if event.type == "response.output_text.delta":
        streamer.append(markdown_text=f"{event.delta}")
    else:
        continue

feedback_block = create_feedback_block()
streamer.stop(blocks=feedback_block)

🔠 Text Streaming Methods

Alternative to the Text Streaming Helper is to call the individual methods.

1) client.chat_startStream

First, start a chat text stream to stream a response to any message:

@app.message()
def handle_message(message, client, context, event, message):
    # Start a new message stream
    stream_response = client.chat_startStream(
        channel=channel_id,
        recipient_team_id=team_id,
        recipient_user_id=user_id,
        thread_ts=thread_ts,
    )
    stream_ts = stream_response["ts"]

2) client.chat_appendStream

After starting a chat text stream, you can then append text to it in chunks (often from your favourite LLM SDK) to convey a streaming effect:

for event in returned_message:
    if event.type == "response.output_text.delta":
        client.chat_appendStream(
            channel=channel_id, 
            ts=stream_ts, 
            markdown_text=f"{event.delta}"
        )
    else:
        continue

3) client.chat_stopStream

Lastly, you can stop the chat text stream to finalize your message:

client.chat_stopStream(
    channel=channel_id, 
    ts=stream_ts,
    blocks=feedback_block
)

👍🏻 Feedback Buttons

Add feedback buttons to the bottom of a message, after stopping a text stream, to gather user feedback:

def create_feedback_block() -> List[Block]:
    blocks: List[Block] = [
        ContextActionsBlock(
            elements=[
                FeedbackButtonsElement(
                    action_id="feedback",
                    positive_button=FeedbackButtonObject(
                        text="Good Response",
                        accessibility_label="Submit positive feedback on this response",
                        value="good-feedback",
                    ),
                    negative_button=FeedbackButtonObject(
                        text="Bad Response",
                        accessibility_label="Submit negative feedback on this response",
                        value="bad-feedback",
                    ),
                )
            ]
        )
    ]
    return blocks

@app.message()
def handle_message(message, client):
    # ... previous streaming code ...
    
    # Stop the stream and add feedback buttons
    feedback_block = create_feedback_block()
    client.chat_stopStream(
        channel=channel_id, 
        ts=stream_ts, 
        blocks=feedback_block
    )

Ⓜ️ Markdown Text Support

chat_postMessage supports markdown_text

response = client.chat_postMessage(
    channel="C111",
    markdown_text=markdown_content,
)

Learn more in slackapi/python-slack-sdk#1718

🧩 Markdown Block

📚 https://docs.slack.dev/reference/block-kit/blocks/markdown-block/

from slack_sdk.models.blocks import MarkdownBlock
...

@app.message("hello")
def message_hello(say):
    say(
        blocks=[
            MarkdownBlock(text="**lets's go!**"),
        ],
        text="let's go!",
    )

Learn more in slackapi/python-slack-sdk#1748

🎞️ Workflows Featured Methods

Add support for the workflows.featured.{add|list|remove|set} methods:

app.client.workflows_featured_add(channel_id="C0123456789", trigger_ids=["Ft0123456789"])
app.client.workflows_featured_list(channel_ids="C0123456789")
app.client.workflows_featured_remove(channel_id="C0123456789", trigger_ids=["Ft0123456789"])
app.client.workflows_featured_set(channel_id="C0123456789", trigger_ids=["Ft0123456789"])

Learn more in slackapi/python-slack-sdk#1712

What's Changed

👾 Enhancements

  • feat: add ai-enabled features text streaming methods, feedback blocks, and loading state in #1387 - Thanks @zimeg!

📚 Documentation

  • docs: add ai provider token instructions in #1340 - Thanks @zimeg!
  • docs: updates for combined quickstart in #1378 - Thanks @haleychaas!
  • docs: replace links from api.slack.com to docs.slack.dev redirects in #1383 - Thanks @zimeg!

🤖 Dependencies

  • chore(deps): update pytest-cov requirement from <7,>=3 to >=3,<8 in #1365 - Thanks @dependabot[bot]!
  • chore(deps): bump actions/setup-python from 5.6.0 to 6.0.0 in #1363 - Thanks @dependabot[bot]!
  • chore(deps): bump actions/checkout from 4.2.2 to 5.0.0 in #1362 - Thanks @dependabot[bot]!
  • chore(deps): bump actions/stale from 9.1.0 to 10.0.0 in #1361 - Thanks @dependabot[bot]!
  • chore(deps): bump codecov/codecov-action from 5.4.3 to 5.5.1 in #1364 - Thanks @dependabot[bot]!
  • build: require cheroot<11 with adapter test dependencies in #1375 - Thanks @zimeg!
  • build(deps): remove pytest lower bounds from testing requirements in #1333 - Thanks @zimeg!
  • chore(deps): bump mypy from 1.17.1 to 1.18.2 in #1379 - Thanks @dependabot[bot]!

🧰 Maintenance

  • ci: post regression notifications if scheduled tests do not succeed in #1376 - Thanks @zimeg!
  • build: install dependencies needed to autogenerate reference docs in #1377 - Thanks @zimeg!
  • version 1.26.0 in #1388 - Thanks @zimeg!

Milestone: https://github.com/slackapi/bolt-python/milestone/94?closed=1
Full Changelog: v1.25.0...v1.26.0
Package: https://pypi.org/project/slack-bo...

Read more

Contributors

zimeg, dependabot, and haleychaas
Assets 2
Loading

version 1.25.0

09 Sep 19:52
@WilliamBergamin WilliamBergamin
v1.25.0
3274d7a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
version 1.25.0

What's Changed

Changes ⚠️

Docs 📖

Maintenance 🏗️

References

Contributors

WilliamBergamin and lukegalbraithrussell
Loading

version 1.24.0

27 Aug 19:02
@WilliamBergamin WilliamBergamin
v1.24.0
67b873d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
version 1.24.0

Changes

Beta feature

maintenance 🏗️

docs 📚

dependabot :dependabot:

  • chore(deps): update sanic requirement from <25,>=21 to >=21,<26 by @dependabot[bot] in #1285
  • chore(deps): update falcon requirement from <4,>=2 to >=2,<5 by @dependabot[bot] in #1286
  • chore(deps): bump the react group in /docs with 2 updates by @dependabot[bot] in #1288
  • chore(deps): bump flake8 from 7.1.2 to 7.2.0 by @dependabot[bot] in #1287
  • chore(deps): bump image-size from 1.2.0 to 1.2.1 in /docs by @dependabot[bot] in #1291
  • chore(deps): bump estree-util-value-to-estree from 3.3.2 to 3.3.3 in /docs by @dependabot[bot] in #1294
  • chore(deps): bump http-proxy-middleware from 2.0.7 to 2.0.9 in /docs by @dependabot[bot] in #1299
  • chore(deps): bump codecov/test-results-action from 1.1.0 to 1.1.1 by @dependabot[bot] in #1310
  • chore(deps): bump the docusaurus group in /docs with 5 updates by @dependabot[bot] in #1311
  • chore(deps): bump mypy from 1.15.0 to 1.16.0 by @dependabot[bot] in #1309
  • chore(deps): bump brace-expansion from 1.1.11 to 1.1.12 in /docs by @dependabot[bot] in #1321
  • chore(deps): bump the docusaurus group in /docs with 5 updates by @dependabot[bot] in #1325
  • chore(deps): bump flake8 from 7.2.0 to 7.3.0 by @dependabot[bot] in #1326
  • chore(deps): bump mypy from 1.16.0 to 1.16.1 by @dependabot[bot] in #1327
  • chore(deps): bump on-headers and compression in /docs by @dependabot[bot] in #1336
  • chore(deps): update pytest requirement from <8.4,>=6.2.5 to >=6.2.5,<8.5 by @dependabot[bot] in #1328
  • chore(deps): bump mypy from 1.16.1 to 1.17.1 by @dependabot[bot] in #1343
  • chore(deps): bump the react group in /docs with 2 updates by @dependabot[bot] in #1344
  • chore(deps): bump slackapi/slack-github-action from 2.1.0 to 2.1.1 by @dependabot[bot] in #1345

References

Contributors

zimeg, WilliamBergamin, and 4 other contributors
Loading

version 1.23.0

19 Mar 19:00
@WilliamBergamin WilliamBergamin
v1.23.0
5c7974a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
version 1.23.0

Changes

fixes 🏗️

docs 📚

dependabot :dependabot:

  • chore(deps): bump mypy from 1.13.0 to 1.14.1 by @dependabot in #1234
  • chore(deps): bump prism-react-renderer from 2.4.0 to 2.4.1 in /docs by @dependabot in #1232
  • chore(deps): update sanic requirement from <24,>=22 to >=22,<25 by @dependabot in #1233
  • chore(deps): bump actions/stale from 9.0.0 to 9.1.0 by @dependabot in #1244
  • chore(deps): bump the docusaurus group in /docs with 5 updates by @dependabot in #1243
  • chore(deps): bump mypy from 1.14.1 to 1.15.0 by @dependabot in #1258
  • chore(deps): update websockets requirement from <15 to <16 by @dependabot in #1260
  • chore(deps): bump flake8 from 6.0.0 to 7.1.2 by @dependabot in #1259
  • chore(deps): bump the react group in /docs with 2 updates by @dependabot in #1265
  • chore(deps): bump prismjs from 1.29.0 to 1.30.0 in /docs by @dependabot in #1269
  • chore(deps): bump @babel/runtime from 7.26.0 to 7.26.10 in /docs by @dependabot in #1275
  • chore(deps): bump @babel/helpers from 7.26.0 to 7.26.10 in /docs by @dependabot in #1273
  • chore(deps): bump @babel/runtime-corejs3 from 7.26.9 to 7.26.10 in /docs by @dependabot in #1274

Relevant changes

We've fixed a regression around the logger, by default the logger used by the WebClient will be the same as the one used by the Bolt application. If the WebClient defines its own logger then it will be used:

my_logger = logging.getLogger("my_logger")
app = App(client=WebClient(token=os.environ.get("SLACK_BOT_TOKEN"), logger=my_logger))

@app.command("/sample-command")
def sample_command(ack: Ack, client: WebClient):
    ack()
    assert client.logger.name == my_logger.name

New Contributors

References

Contributors

slackapi, zimeg, and 5 other contributors
Loading

version 1.22.0

18 Dec 18:18
@WilliamBergamin WilliamBergamin
v1.22.0
9390d0a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
version 1.22.0

Changes

Dependabot

References

Contributors

zimeg, WilliamBergamin, and 2 other contributors
Loading

version 1.21.3

05 Dec 23:02
@seratch seratch
v1.21.3
d0a701c
Compare
Choose a tag to compare
version 1.21.3

Changes

  • #1187 Add title argument to SetSuggestedPrompts arguments - Thanks @seratch
  • #1216 Expose loop param on asyncio-based AsyncSocketModeHandler - Thanks @jantman
  • #1202 Socket Mode: Failed to connect (error: string argument without an encoding) w/ Azure App Service + aiohttp 3.11.2 - Thanks @seratch @jeremybeeman
  • #1199 Resolve Falcon 5.x type hint compatibility issue - Thanks @seratch

References

Contributors

seratch, jantman, and jeremybeeman
Loading

version 1.21.2

25 Oct 05:43
@seratch seratch
v1.21.2
9de07b1
Compare
Choose a tag to compare
version 1.21.2

Changes

  • #1186 Improve metadata resolution timing in assistant app's say method - Thanks @seratch

References

Contributors

seratch
Loading

version 1.21.1

22 Oct 06:02
@seratch seratch
v1.21.1
18a9135
Compare
Choose a tag to compare
version 1.21.1

Changes

  • #1184 Fix a bug where parsing assistant thread message event fails for beta feature enabled apps - Thanks @seratch

References

Contributors

seratch
Loading

version 1.21.0

17 Oct 02:32
@seratch seratch
v1.21.0
a57619e
Compare
Choose a tag to compare
version 1.21.0

New Features

Agents & Assistants

A better Agents & Assistants support in Bolt is now available!

While you already can implement your agents using app.event(...) listeners for assistant_thread_started, assistant_thread_context_changed, and message events, Bolt offers a simpler approach. You just need to create an Assistant instance, attach the needed event handlers to it, and then add the assistant to your App instance.

assistant = Assistant()

# This listener is invoked when a human user opened an assistant thread
@assistant.thread_started
def start_assistant_thread(say: Say, set_suggested_prompts: SetSuggestedPrompts):
    # Send the first reply to the human who started chat with your app's assistant bot
    say(":wave: Hi, how can I help you today?")

    # Setting suggested prompts is optional
    set_suggested_prompts(
        prompts=[
            # If the suggested prompt is long, you can use {"title": "short one to display", "message": "full prompt"} instead
            "What does SLACK stand for?",
            "When Slack was released?",
        ],
    )

# This listener is invoked when the human user sends a reply in the assistant thread
@assistant.user_message
def respond_in_assistant_thread(
    payload: dict,
    logger: logging.Logger,
    context: BoltContext,
    set_status: SetStatus,
    say: Say,
    client: WebClient,
):
    try:
        # Tell the human user the assistant bot acknowledges the request and is working on it
        set_status("is typing...")

        # Collect the conversation history with this user
        replies_in_thread = client.conversations_replies(
            channel=context.channel_id,
            ts=context.thread_ts,
            oldest=context.thread_ts,
            limit=10,
        )
        messages_in_thread: List[Dict[str, str]] = []
        for message in replies_in_thread["messages"]:
            role = "user" if message.get("bot_id") is None else "assistant"
            messages_in_thread.append({"role": role, "content": message["text"]})

        # Pass the latest prompt and chat history to the LLM (call_llm is your own code)
        returned_message = call_llm(messages_in_thread)

        # Post the result in the assistant thread
        say(text=returned_message)

    except Exception as e:
        logger.exception(f"Failed to respond to an inquiry: {e}")
        # Don't forget sending a message telling the error
        # Without this, the status 'is typing...' won't be cleared, therefore the end-user is unable to continue the chat
        say(f":warning: Sorry, something went wrong during processing your request (error: {e})")

# Enable this assistant middleware in your Bolt app
app.use(assistant)

Please refer to https://tools.slack.dev/bolt-python/concepts/assistant/ and https://github.com/slack-samples/bolt-python-assistant-template for more details.

Changes

  • #1162 Add Agents & Assistants support - Thanks @seratch
  • #1142 Add listener_runner to context object to enable developers to leverage lazy listeners in middleware - Thanks @seratch
  • #1170 Fix double quoted img alt text in the default OAuth page rendering - @toofishes
  • #1173 Expose auto_acknowledge option for custom function handlers - Thanks @WilliamBergamin
  • #1143 Remove Optional typing of context.client - Thanks @WilliamBergamin
  • #1164 Simplify Python code snippets in authorization.md - Thanks @arkid15r

References

Contributors

seratch, toofishes, and 2 other contributors
Loading

version 1.20.1

23 Aug 14:40
@WilliamBergamin WilliamBergamin
v1.20.1
3aa9c30
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
version 1.20.1

Changes

New Contributors

References

Contributors

seratch, WilliamBergamin, and RohanArepally
Loading