Overview
Prerequisites:
- This feature is available on workspaces with DinoAI programmable agents enabled.
- Your API keys must have access to the DinoAI Agents API.
These examples authenticate with an account API key (
api_secret="prdm_cmp_..." plus workspace_uid), which requires paradime-io 6.0.0 or later. Legacy workspace API keys (api_key + api_secret) are still supported. See Getting Started.Trigger an agent run
Triggers a DinoAI programmable agent run. At least one ofagent or message must be provided.
Name of the YAML-defined agent to load (matches the file name under
.dinoai/agents/ without the .yml extension).Custom prompt appended to the agent’s context. When only
agent is provided, the run starts with the agent’s role/goal/backstory.Slack channel ID the run should post into (e.g.
"C0123456789"). Must be provided together with slack_thread.Slack thread timestamp the run should reply in (e.g.
"1714142436.001200"). Must be provided together with slack_channel.Git branch, tag or commit SHA the agent checks out before creating its working branch. Defaults to the repository’s default branch.
Contains
ok, agent_session_id, and status (always the literal string "queued" on accept — poll with get_run for live status).Trigger an agent run and wait for completion
Triggers a DinoAI agent run and blocks until it reachesCOMPLETED or FAILED.
Git branch, tag or commit SHA the agent checks out before creating its working branch. Defaults to the repository’s default branch.
The final run state, including
status, all messages, child_session_ids, and workspace_uid.Raises DinoaiAgentRunFailedException if the run finishes with status FAILED, and TimeoutError if the run does not complete within timeout seconds.Send a follow-up message
Sends a follow-up message to an active DinoAI agent session. The agent pod stays alive for up to 24 hours since the last message; follow-ups resume the same conversation with full context.Get an agent run
Fetches the current state of a DinoAI agent run.Also return
steps, every step so far with the tool calls, as the session panel in the app shows them, and startup_steps, the checklist while the agent pod boots. Added in SDK 6.8.0.With
include_steps, also return each tool’s input and output. They can hold raw query results and file contents.With
include_steps, return only the steps with a greater index. Pass the last index you read to poll for new steps.Contains
ok, status (one of QUEUED, RUNNING, COMPLETED, FAILED, or EXPIRED; EXPIRED is terminal and means the agent pod never started), messages (what the agent delivered, each with ts as a string epoch timestamp, role, content), child_session_ids (sub-agents spawned during the run), and workspace_uid. With include_steps, also steps (each a DinoaiAgentStep with index, role, tool_name, tool_input, content, and truncated) and startup_steps (each a DinoaiAgentStartupStep with label and done). Both are None unless requested, or when the steps couldn’t be read.