takt/resources/global/en/workflows/research.yaml
2026-01-25 15:16:27 +09:00

113 lines
3.1 KiB
YAML

# Research Workflow
# A workflow that autonomously executes research tasks
# Planner creates the plan, Digger executes, Supervisor verifies
#
# Flow:
# plan -> dig -> supervise -> COMPLETE (approved)
# -> plan (rejected: restart from planning)
name: research
description: Research workflow - autonomously executes research without asking questions
max_iterations: 10
steps:
- name: plan
agent: ~/.takt/agents/research/planner.md
instruction_template: |
## Workflow Status
- Iteration: {iteration}/{max_iterations}
- Step: plan
## Research Request
{task}
## Supervisor Feedback (for re-planning)
{previous_response}
## Additional User Inputs
{user_inputs}
## Instructions
Create a research plan for the above request.
**Important**: Do not ask the user questions.
- Make assumptions for unclear points and proceed
- If multiple interpretations exist, include all in the research scope
- If there is feedback from Supervisor, incorporate it into the plan
Output [PLANNER:DONE] when the plan is complete.
pass_previous_response: true
transitions:
- condition: done
next_step: dig
- condition: blocked
next_step: ABORT
- name: dig
agent: ~/.takt/agents/research/digger.md
instruction_template: |
## Workflow Status
- Iteration: {iteration}/{max_iterations}
- Step: dig
## Original Research Request
{task}
## Research Plan
{previous_response}
## Additional User Inputs
{user_inputs}
## Instructions
Execute the research according to the plan above.
**Important**: Do not ask the user questions.
- Research within the scope of what can be investigated
- Report items that could not be researched as "Unable to research"
Available tools:
- Web search
- GitHub search (gh command)
- Codebase search
- File reading
Output [DIGGER:DONE] when the research is complete.
pass_previous_response: true
transitions:
- condition: done
next_step: supervise
- condition: blocked
next_step: ABORT
- name: supervise
agent: ~/.takt/agents/research/supervisor.md
instruction_template: |
## Workflow Status
- Iteration: {iteration}/{max_iterations}
- Step: supervise (research quality evaluation)
## Original Research Request
{task}
## Digger's Research Results
{previous_response}
## Instructions
Evaluate the research results and determine if they adequately answer the original request.
**Evaluation Output**:
- [SUPERVISOR:APPROVE] - Research complete, results are sufficient
- [SUPERVISOR:REJECT] - Insufficient, restart from planning (specify what's missing)
**Important**: If there are issues, include specific instructions for the Planner.
pass_previous_response: true
transitions:
- condition: approved
next_step: COMPLETE
- condition: rejected
next_step: plan
initial_step: plan