feat(council): add council advisory skill with parallel/sequential/debate flows
- 3 advisors (Pragmatist, Visionary, Skeptic) + 1 Referee subagent - Default: parallel + synthesis flow - Prompt templates in references/prompts.md - Model tier selection based on topic complexity - Added TODO tasks for personality depth and skill name revisit
This commit is contained in:
zap
16
memory/2026-03-05.md
Normal file
16
memory/2026-03-05.md
Normal file
@@ -0,0 +1,16 @@
|
||||
# 2026-03-05
|
||||
|
||||
## Council skill created
|
||||
- Built `skills/council/` — multi-perspective advisory council using subagents.
|
||||
- Design decisions (agreed with Will):
|
||||
- Implemented as a **skill** (not standalone agents).
|
||||
- 3 advisors (Pragmatist, Visionary, Skeptic) + 1 Referee = 4 subagents total.
|
||||
- Referee is a separate subagent (not the session model) — can use a stronger model tier.
|
||||
- Default flow: **Parallel + Synthesis**. Sequential and Debate flows also available.
|
||||
- Final output includes individual advisor perspectives (collapsed/summarized) + referee verdict.
|
||||
- Model tier chosen per-invocation based on topic complexity.
|
||||
- Files: `SKILL.md`, `references/prompts.md`, `scripts/council.sh` (reference doc).
|
||||
- Validated with skill-creator quick_validate.
|
||||
- Two TODOs added to `memory/tasks.json`:
|
||||
- Revisit advisor personality depth (richer backstories).
|
||||
- Revisit skill name ("council" is placeholder).
|
||||
@@ -28,5 +28,29 @@
|
||||
"Upstream patch committed in external/openclaw-upstream on branch fix/tui-hide-internal-runtime-context commit 0f66a4547 (suppress internal runtime completion context blocks in TUI formatter).",
|
||||
"Validation: pnpm test:fast completed successfully (812 files / 6599 tests passing) at 2026-03-04T22:53:29Z"
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "task-20260305-0838-council-personality-depth",
|
||||
"created_at": "2026-03-05T08:38:00Z",
|
||||
"title": "Revisit council subagent personality depth",
|
||||
"owner": "zap",
|
||||
"priority": "low",
|
||||
"status": "open",
|
||||
"details": "Explore richer personality backstories and communication styles for council advisor agents beyond the current role/lens/stance pattern.",
|
||||
"notes": [
|
||||
"From council skill brainstorm session 2026-03-05."
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "task-20260305-0838-council-skill-name",
|
||||
"created_at": "2026-03-05T08:38:00Z",
|
||||
"title": "Revisit council skill name",
|
||||
"owner": "zap",
|
||||
"priority": "low",
|
||||
"status": "open",
|
||||
"details": "council works for now but revisit whether a better name fits as the feature matures.",
|
||||
"notes": [
|
||||
"From council skill brainstorm session 2026-03-05."
|
||||
]
|
||||
}
|
||||
]
|
||||
|
||||
73
skills/council/SKILL.md
Normal file
73
skills/council/SKILL.md
Normal file
@@ -0,0 +1,73 @@
|
||||
---
|
||||
name: council
|
||||
description: "Convene a council of AI advisor agents with distinct perspectives to deliberate on a topic, then synthesize their views into a verdict. Use when: (1) user asks for multi-perspective analysis, (2) wants to brainstorm with diverse viewpoints, (3) requests a council or advisors opinion, (4) needs a balanced decision on a complex question. Supports parallel (default), sequential, and debate flows. NOT for: simple factual lookups, single-perspective tasks, or quick one-liner answers."
|
||||
---
|
||||
|
||||
# Council Skill
|
||||
|
||||
Spawn a council of 3 advisor subagents + 1 referee subagent to deliberate on a topic.
|
||||
Each advisor has a distinct personality/lens. The referee synthesizes their output into a
|
||||
final verdict with collapsed advisor perspectives.
|
||||
|
||||
## Advisor Roster (default)
|
||||
|
||||
| Role | Lens | System stance |
|
||||
|--------------|---------------------------------|----------------------------------|
|
||||
| Pragmatist | Feasibility, cost, effort | "Can we actually do this?" |
|
||||
| Visionary | Long-term potential, innovation | "What if we went bigger?" |
|
||||
| Skeptic | Risk, failure modes, edge cases | "What could go wrong?" |
|
||||
|
||||
The referee is a separate agent: balanced, fair, synthesis-oriented.
|
||||
|
||||
## Flows
|
||||
|
||||
Three deliberation flows are available. Default is **parallel**.
|
||||
|
||||
### 1. Parallel + Synthesis (default)
|
||||
|
||||
1. Spawn all 3 advisors simultaneously via `sessions_spawn` (mode=run).
|
||||
2. Each advisor receives the same topic prompt with their personality instructions.
|
||||
3. Wait for all 3 to complete (push-based — they announce when done).
|
||||
4. Spawn the referee with all 3 advisor outputs as context.
|
||||
5. Referee produces the final verdict.
|
||||
|
||||
### 2. Sequential Rounds
|
||||
|
||||
1. Spawn advisors one at a time, each seeing prior advisor outputs.
|
||||
2. After all advisors, spawn referee with full thread.
|
||||
3. Optionally run a rebuttal round (advisors respond to each other).
|
||||
|
||||
### 3. Debate
|
||||
|
||||
1. Spawn advisors in parallel for initial takes.
|
||||
2. Share outputs across advisors for rebuttals (1-2 rounds).
|
||||
3. Referee moderates and calls convergence.
|
||||
|
||||
## Model Selection
|
||||
|
||||
Pick model tier based on topic complexity:
|
||||
|
||||
- **Light topics** (casual brainstorm, simple pros/cons): use default model for advisors and referee.
|
||||
- **Medium topics** (architecture decisions, strategy): use default model for advisors, stronger model for referee.
|
||||
- **Heavy topics** (critical decisions, deep analysis): use stronger model for all agents.
|
||||
|
||||
The caller (main agent) determines tier before spawning.
|
||||
|
||||
## Prompt Templates
|
||||
|
||||
See `references/prompts.md` for full advisor and referee prompt templates with placeholders.
|
||||
|
||||
## Implementation
|
||||
|
||||
Read `scripts/council.sh` for the orchestration logic.
|
||||
For programmatic invocation, the main agent can also call `sessions_spawn` directly
|
||||
following the patterns above.
|
||||
|
||||
## Configuration
|
||||
|
||||
Advisor personalities can be customized per-invocation by overriding the roster.
|
||||
Default roster and prompt templates live in `references/prompts.md`.
|
||||
|
||||
## TODO (revisit later)
|
||||
- Revisit subagent personality depth — richer backstories, communication styles
|
||||
- Revisit skill name — "council" works for now
|
||||
92
skills/council/references/prompts.md
Normal file
92
skills/council/references/prompts.md
Normal file
@@ -0,0 +1,92 @@
|
||||
# Council Prompt Templates
|
||||
|
||||
## Default Advisor Roster
|
||||
|
||||
### Pragmatist
|
||||
- **Role**: Pragmatist
|
||||
- **Lens**: Feasibility, cost, effort, timeline
|
||||
- **Stance**: "Can we actually do this?"
|
||||
- **Style**: Direct, grounded, numbers-oriented. Asks "how" more than "why."
|
||||
|
||||
### Visionary
|
||||
- **Role**: Visionary
|
||||
- **Lens**: Long-term potential, innovation, opportunity cost of inaction
|
||||
- **Stance**: "What if we went bigger?"
|
||||
- **Style**: Ambitious, future-oriented. Pushes boundaries but acknowledges when dreaming.
|
||||
|
||||
### Skeptic
|
||||
- **Role**: Skeptic
|
||||
- **Lens**: Risk, failure modes, edge cases, unintended consequences
|
||||
- **Stance**: "What could go wrong?"
|
||||
- **Style**: Cautious, thorough, devil's advocate. Not negative — protective.
|
||||
|
||||
## Advisor System Prompt
|
||||
|
||||
```
|
||||
You are the {ROLE} advisor on a council deliberating a topic.
|
||||
|
||||
Your lens: {LENS}
|
||||
Your typical stance: {STANCE}
|
||||
Your communication style: {STYLE}
|
||||
|
||||
Rules:
|
||||
- Stay in character. Argue from your perspective consistently.
|
||||
- Be concise but substantive (200-400 words).
|
||||
- Acknowledge trade-offs honestly — don't strawman other views.
|
||||
- Reference specific aspects of the topic, not generic platitudes.
|
||||
- End with your key recommendation in 1-2 sentences.
|
||||
|
||||
Topic:
|
||||
{TOPIC}
|
||||
```
|
||||
|
||||
## Referee System Prompt
|
||||
|
||||
```
|
||||
You are the Referee of an advisory council. You have received perspectives from multiple advisors with different viewpoints on the same topic.
|
||||
|
||||
Your job:
|
||||
1. Identify points of agreement and disagreement across all advisors.
|
||||
2. Weigh the arguments fairly — no advisor gets preferential treatment.
|
||||
3. Produce a final verdict with clear reasoning.
|
||||
4. Be honest when the answer is genuinely uncertain.
|
||||
|
||||
Output format (use these exact headers):
|
||||
|
||||
## Advisor Perspectives (Summary)
|
||||
For each advisor, provide a 2-3 sentence summary of their position and key argument.
|
||||
|
||||
## Points of Agreement
|
||||
What the advisors broadly agree on.
|
||||
|
||||
## Key Tensions
|
||||
Where they disagree and why each side has merit.
|
||||
|
||||
## Verdict
|
||||
Your synthesized recommendation with reasoning. Be specific and actionable.
|
||||
|
||||
## Confidence
|
||||
Rate your confidence: high / medium / low, with a one-line explanation of what would change your mind.
|
||||
|
||||
---
|
||||
|
||||
Advisor outputs below:
|
||||
|
||||
{ADVISOR_OUTPUTS}
|
||||
```
|
||||
|
||||
## Rebuttal Round Prompt (for Sequential/Debate flows)
|
||||
|
||||
```
|
||||
You are the {ROLE} advisor. You've seen the other advisors' perspectives on this topic.
|
||||
|
||||
Review their arguments and respond:
|
||||
- Where do you agree or concede ground?
|
||||
- Where do you push back, and why?
|
||||
- Has anything changed your recommendation?
|
||||
|
||||
Keep it to 100-200 words.
|
||||
|
||||
Other advisor outputs:
|
||||
{OTHER_OUTPUTS}
|
||||
```
|
||||
54
skills/council/scripts/council.sh
Normal file
54
skills/council/scripts/council.sh
Normal file
@@ -0,0 +1,54 @@
|
||||
#!/usr/bin/env bash
|
||||
# council.sh — Reference implementation for council orchestration.
|
||||
#
|
||||
# This script is NOT executed directly. It documents the orchestration
|
||||
# logic the main agent follows when invoking the council skill.
|
||||
#
|
||||
# The main agent uses sessions_spawn (mode=run) to create each subagent.
|
||||
#
|
||||
# ─── PARALLEL FLOW (default) ───────────────────────────────────────
|
||||
#
|
||||
# 1. Build advisor prompts from references/prompts.md templates.
|
||||
# 2. Spawn 3 advisor subagents simultaneously:
|
||||
#
|
||||
# sessions_spawn(
|
||||
# task = "<advisor system prompt>\n\nTopic: <topic>",
|
||||
# mode = "run",
|
||||
# label = "council-<role>", # e.g. council-pragmatist
|
||||
# model = "<chosen model tier>", # optional override
|
||||
# )
|
||||
#
|
||||
# 3. Wait for all 3 completion events (push-based).
|
||||
# 4. Collect advisor outputs.
|
||||
# 5. Spawn referee subagent:
|
||||
#
|
||||
# sessions_spawn(
|
||||
# task = "<referee system prompt with all advisor outputs>",
|
||||
# mode = "run",
|
||||
# label = "council-referee",
|
||||
# model = "<chosen model tier>", # may be stronger than advisors
|
||||
# )
|
||||
#
|
||||
# 6. Deliver referee output to user with individual advisor perspectives
|
||||
# included as collapsed summaries.
|
||||
#
|
||||
# ─── SEQUENTIAL FLOW ──────────────────────────────────────────────
|
||||
#
|
||||
# Same as parallel but advisors are spawned one at a time.
|
||||
# Each subsequent advisor sees prior outputs in their prompt.
|
||||
# Optional rebuttal round before referee.
|
||||
#
|
||||
# ─── DEBATE FLOW ──────────────────────────────────────────────────
|
||||
#
|
||||
# 1. Parallel initial takes (same as parallel flow steps 1-4).
|
||||
# 2. Rebuttal round: respawn each advisor with all other outputs visible.
|
||||
# 3. Collect rebuttals.
|
||||
# 4. Spawn referee with initial takes + rebuttals.
|
||||
#
|
||||
# ─── MODEL TIER SELECTION ─────────────────────────────────────────
|
||||
#
|
||||
# Light: advisors=default, referee=default
|
||||
# Medium: advisors=default, referee=stronger (e.g. opus-tier)
|
||||
# Heavy: advisors=stronger, referee=stronger
|
||||
#
|
||||
# The main agent decides tier before spawning based on topic complexity.
|
||||
Reference in New Issue
Block a user