Skip to main content

Python SDK for Mobius agent loops and workers

Project description

deepnoodle-mobius

Python SDK for Mobius agent sessions, loops, and workers.

Multi-tool agent quickstart

import os
import deepnoodle.mobius as mobius

client = mobius.Client(mobius.ClientOptions(
    api_key=os.environ["MOBIUS_API_KEY"],
    project=os.environ["MOBIUS_PROJECT"],
))

try:
    turn = client.invoke_agent(mobius.InvokeAgentOptions(
        agent_name="launch-scout",
        idempotency_key=inbound_message_id,
        content=[{"type": "text", "text": "Check the name and create a shortlist."}],
        config=mobius.InlineAgentConfig(toolkits=[
            mobius.InlineToolkit(name="naming", actions=["naming.domain.check"]),
            mobius.InlineToolkit(name="shortlists", actions=["shortlists.create"]),
        ]),
    ))
    for update in turn.updates():
        for message in update.transcript.renderable_messages():
            print(mobius.text_of(message))
            for block in message["content"]:
                if block.get("type") == "tool_use":
                    tool = mobius.normalize_tool_use(block)
                    print((tool.resolved_action or {}).get("name", tool.wire_name))
    if turn.error:
        raise turn.error
except mobius.MobiusAPIError as error:
    if error.code == "session_turn_active":
        # Choose explicitly: wait and invoke again, or client.nudge_session(...).
        pass
    else:
        raise

Use messages() for the lossless protocol view and renderable_messages() for UI. normalize_tool_use() preserves the model-facing wire fields and prefers Mobius' persisted canonical action identity. The cross-language helper guide covers nudges, reconnection, diagnostics, session management, persistence ordering, and the server-to-browser boundary.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

deepnoodle_mobius-0.0.51.tar.gz (97.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

deepnoodle_mobius-0.0.51-py3-none-any.whl (103.1 kB view details)

Uploaded Python 3

File details

Details for the file deepnoodle_mobius-0.0.51.tar.gz.

File metadata

  • Download URL: deepnoodle_mobius-0.0.51.tar.gz
  • Upload date:
  • Size: 97.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for deepnoodle_mobius-0.0.51.tar.gz
Algorithm Hash digest
SHA256 9e226e156f2970ee337f69999fc1c246d4e79da133528298ec9e110cb5006238
MD5 b79d55201221bc26abb56b6498de62a6
BLAKE2b-256 0d126579bdb56ef9e342e6e85bdfa9d84c4cf26456de00f16dceb9e3d8a17cf8

See more details on using hashes here.

Provenance

The following attestation bundles were made for deepnoodle_mobius-0.0.51.tar.gz:

Publisher: release-pypi.yml on deepnoodle-ai/mobius

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file deepnoodle_mobius-0.0.51-py3-none-any.whl.

File metadata

File hashes

Hashes for deepnoodle_mobius-0.0.51-py3-none-any.whl
Algorithm Hash digest
SHA256 41a26dd3853bc2909f8b758c60ddecad72a920a374dfd0132f932d50c0939bc1
MD5 0ed0383a4eac51853ae85b8a85a0f9ba
BLAKE2b-256 4f9f934db387abe66f26a6f8dae694be6fe7ff8ea88024170aa84f8789a4cd23

See more details on using hashes here.

Provenance

The following attestation bundles were made for deepnoodle_mobius-0.0.51-py3-none-any.whl:

Publisher: release-pypi.yml on deepnoodle-ai/mobius

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page