pae/crimson_leaf_publishing
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(clp): route intake to Nova (CEO), clean task type overlaps

Browse Source 
- InputFromUser.yml: route planning tasks to Nova (not Selene)
- Nova: restored planning to supported_templates (is CEO)
- Selene: removed planning (now boardroom/quick/hire_agent only)
- Atlas: removed planning+quick, added blog_research
- Nova: removed quick (Selene handles quick)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
David Baity
2026-03-12 01:27:28 -04:00
parent 50749f8e2b
commit d90eceda0c
4 changed files with 11 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
templates/InputFromUser.yml
View File

@@ -21,12 +21,12 @@ steps:
hint: |
Your ONLY job is to route this message to the right place.
You do NOT decide what work to do. You do NOT pick templates. You do NOT assign agents.
The CEO (Selene) will receive this message and decide the workflow.
The CEO (Nova) will receive this message and decide the workflow.
Classify the message into ONE of these categories:
a) WORK REQUEST — the operator wants something done (write, research, build, plan, etc.)
Create ONE task for Selene with task_type "planning". Include the full message as the description.
Create ONE task for Nova with task_type "planning". Include the full message as the description.
b) SIMPLE QUESTION / CHAT — just a question or conversational remark.
Reply directly. Do NOT create a task.
@@ -49,7 +49,7 @@ steps:
Emit procure_company with name, slug, and business_plan extracted from the message.
The slug must be lowercase kebab-case (e.g. "Crimson Leaf Publishing" → "crimson-leaf-publishing").
The business_plan should capture the description/focus from the message (may be empty string if none given).
Do NOT route this to Selene. Do NOT create a planning task.
Do NOT route this to Nova. Do NOT create a planning task.
- If NO company name was provided:
Do NOT emit procure_company.
Instead, reply directly with a name suggestion based on the description.
@@ -60,14 +60,14 @@ steps:
- Emit ONE `hire_agent` action PER agent role requested.
- Set `task_type` to the role name (e.g. "Writer", "Researcher", "Strategist").
- Set `context` to any extra description about the role (optional — use empty string if none given).
- Do NOT route to Selene. Do NOT create a planning task.
- Do NOT route to Nova. Do NOT create a planning task.
CRITICAL: For category (a), ALWAYS assign to Selene with task_type "planning".
CRITICAL: For category (a), ALWAYS assign to Nova with task_type "planning".
Do NOT try to decide the right agent, template, or workflow yourself.
Selene is the CEO. She decides. You route.
For category (g) with a name, emit procure_company directly — Selene is NOT involved.
Nova is the CEO. She decides. You route.
For category (g) with a name, emit procure_company directly — Nova is NOT involved.
For category (g) without a name, reply only — do NOT create any task or action.
For category (h), emit one hire_agent action per role — Selene is NOT involved.
For category (h), emit one hire_agent action per role — Nova is NOT involved.
OUTPUT FORMAT: Your response IS the user-facing reply. Write it directly.
- For work requests: "Task Created: [task name]"
@@ -85,7 +85,7 @@ steps:
task_name: "string — short name (create_task only)"
description: "string — the operator's full message verbatim, plus project context (create_task only)"
agents:
- "Selene"
- "Nova"
task_type: "planning or role name (planning for create_task; role name e.g. Writer for hire_agent)"
note: "string — insight to store (save_nugget only)"
subject: "string — what to look up (status_query only)"
@@ -101,3 +101,4 @@ steps:
target: discussion
adjudication:
enabled: false