Feature/multi run agent orchestration (WIP) #16
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ystem - Add frontend directory structure to repo layout - Document Agent Trigger DocType with all trigger types - Update Agent DocType fields (removed condition, added statistics) - Add Agent Tool Type DocType documentation - Document agent_hooks.py and agent_scheduler.py modules - Add comprehensive Frontend Architecture section covering: * Technology stack (React 18, TypeScript, Vite, shadcn/ui) * Frontend structure and components * Dashboard framework * Agent management UI * Flow builder * API integration - Add Recent Changes section documenting migrations and additions This update reflects the current state of the codebase including the Agent Trigger system migration and React frontend implementation.
Add two new doctypes for multi-run agent orchestration: - Agent Orchestration Config: Configuration for orchestration mode * Links to Agent * Mode selection (single_multi_run) * Plan template JSON * Policy JSON * Active status flag - Agent Orchestration Run: Tracks orchestration execution * Links to Agent and Orchestration Config * Status tracking (Started, Running, Paused, Halted, Done, Failed) * Budget tracking (used tokens, time, cost estimate) * Plan and scratchpad JSON fields * Halt reason field These doctypes support multi-step reasoning style execution for agents with orchestration capabilities. WIP: Part of multi-run agent orchestration feature.
Add orchestration configuration fields to Agent doctype: - Orchestration tab with enable_orchestration flag - Orchestration mode selection (single_multi_run) - Budget controls: max_steps, time_budget_s, token_budget - Planning configuration: * planning_prompt (Code field) * plan_template_json * step_prompt_template Also includes scheduling and doc event fields for backward compatibility during migration. WIP: Part of multi-run agent orchestration feature.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR introduces the foundation for multi-run agent orchestration, enabling agents to perform multi-step reasoning style execution. This is a work-in-progress feature that adds the necessary data models and documentation updates.
Changes
Documentation Updates
AGENTS.mdwith comprehensive documentation:agent_hooks.pyandagent_scheduler.pymodulesNew DocTypes
Agent Orchestration Config
Configuration DocType for multi-run orchestration:
single_multi_run)Agent Orchestration Run
Execution tracking DocType for orchestration runs:
Agent Doctype Updates
Added orchestration configuration fields:
enable_orchestrationflagorchestration_mode(single_multi_run)max_steps,time_budget_s,token_budgetplanning_prompt(Code field)plan_template_jsonstep_prompt_templateAlso includes scheduling and doc event fields for backward compatibility during migration.
Status
Work in Progress - This PR contains the foundational data models and documentation. Implementation of the orchestration execution logic is pending.
Related
Part of the multi-run agent orchestration feature implementation.
Notes