Compare commits

..

1 Commits

Author SHA1 Message Date
Timmy Agent
2f53409614 feat(lab-005): Deploy AI agent fleet on available laptops (#530)
Some checks failed
Self-Healing Smoke / self-healing-smoke (pull_request) Failing after 27s
Smoke Test / smoke (pull_request) Failing after 29s
Agent PR Gate / gate (pull_request) Failing after 49s
Agent PR Gate / report (pull_request) Successful in 17s
- Add configs/laptop-fleet-manifest.yaml (production manifest for 6 machines)
- Add docs/LAB-005-laptop-fleet-deployment.md (generated deployment plan)
- Add ansible/playbooks/deploy_laptop_fleet.yml (Ansible playbook for Linux laptops)
- Add ansible/inventory/laptops.ini (fleet inventory with role groups)
- Add configs/hermes-laptop-anchor.service (24/7 systemd user service)
- Add configs/hermes-laptop-daylight.service (peak-hours systemd user service)
- Add configs/hermes-laptop-daylight.timer (systemd timer for 10:00 start)
- Expand tests to verify production manifest, plan, playbook, and services
2026-04-22 01:48:33 -04:00
9 changed files with 341 additions and 172 deletions

View File

@@ -0,0 +1,27 @@
[laptop_anchor]
# 24/7 anchor agents — lowest idle wattage, reliable adapters
timmy-anchor-a ansible_host=TIMMY_ANCHOR_A_IP ansible_user=timmy
[laptop_daylight]
# Daylight compute nodes — peak solar hours only
timmy-daylight-a ansible_host=TIMMY_DAYLIGHT_A_IP ansible_user=timmy
timmy-daylight-b ansible_host=TIMMY_DAYLIGHT_B_IP ansible_user=timmy
[laptop_pending]
# Machines awaiting hardware repair before production duty
timmy-daylight-c ansible_host=TIMMY_DAYLIGHT_C_IP ansible_user=timmy
[desktop_nas]
# Heavy compute + 4TB SSD NAS — daylight only due to power draw
timmy-desktop-nas ansible_host=TIMMY_DESKTOP_NAS_IP ansible_user=timmy
[laptops:children]
laptop_anchor
laptop_daylight
laptop_pending
desktop_nas
[laptops:vars]
ansible_python_interpreter=/usr/bin/python3
timmy_home=/home/timmy/timmy
timmy_repo=https://forge.alexanderwhitestone.com/Timmy_Foundation/timmy-home.git

View File

@@ -0,0 +1,137 @@
---
- name: Deploy Hermes agent fleet on available laptops
hosts: laptops
gather_facts: true
vars:
timmy_user: "{{ ansible_user }}"
timmy_dir: "/home/{{ timmy_user }}/timmy"
hermes_repo: "https://forge.alexanderwhitestone.com/Timmy_Foundation/timmy-home.git"
hermes_agent_repo: "https://forge.alexanderwhitestone.com/Timmy_Foundation/hermes-agent.git"
tasks:
- name: Ensure required packages are installed
ansible.builtin.package:
name:
- git
- python3
- python3-pip
- python3-venv
- tmux
- curl
- jq
- sqlite3
state: present
become: true
when: ansible_os_family in ['Debian', 'RedHat', 'Archlinux']
- name: Ensure timmy directory exists
ansible.builtin.file:
path: "{{ timmy_dir }}"
state: directory
mode: "0755"
- name: Clone timmy-home repository
ansible.builtin.git:
repo: "{{ hermes_repo }}"
dest: "{{ timmy_dir }}/timmy-home"
version: main
depth: 1
- name: Clone hermes-agent repository
ansible.builtin.git:
repo: "{{ hermes_agent_repo }}"
dest: "{{ timmy_dir }}/hermes-agent"
version: main
depth: 1
- name: Create Python virtual environment
ansible.builtin.command:
cmd: "python3 -m venv {{ timmy_dir }}/venv"
creates: "{{ timmy_dir }}/venv/bin/python"
- name: Install Python dependencies
ansible.builtin.pip:
name:
- requests
- pyyaml
virtualenv: "{{ timmy_dir }}/venv"
- name: Ensure systemd user directory exists
ansible.builtin.file:
path: "{{ ansible_env.HOME | default('/home/' + timmy_user) }}/.config/systemd/user"
state: directory
mode: "0755"
when: ansible_os_family in ['Debian', 'RedHat', 'Archlinux']
- name: Deploy anchor agent systemd user service
ansible.builtin.template:
src: "../../configs/hermes-laptop-anchor.service"
dest: "{{ ansible_env.HOME | default('/home/' + timmy_user) }}/.config/systemd/user/hermes-laptop-anchor.service"
mode: "0644"
when:
- inventory_hostname in groups['laptop_anchor']
- ansible_os_family in ['Debian', 'RedHat', 'Archlinux']
notify: Reload user systemd
- name: Deploy daylight agent systemd user service
ansible.builtin.template:
src: "../../configs/hermes-laptop-daylight.service"
dest: "{{ ansible_env.HOME | default('/home/' + timmy_user) }}/.config/systemd/user/hermes-laptop-daylight.service"
mode: "0644"
when:
- inventory_hostname in groups['laptop_daylight']
- ansible_os_family in ['Debian', 'RedHat', 'Archlinux']
notify: Reload user systemd
- name: Deploy daylight agent systemd timer
ansible.builtin.template:
src: "../../configs/hermes-laptop-daylight.timer"
dest: "{{ ansible_env.HOME | default('/home/' + timmy_user) }}/.config/systemd/user/hermes-laptop-daylight.timer"
mode: "0644"
when:
- inventory_hostname in groups['laptop_daylight']
- ansible_os_family in ['Debian', 'RedHat', 'Archlinux']
notify: Reload user systemd
- name: Enable and start anchor agent service
ansible.builtin.systemd:
name: hermes-laptop-anchor.service
state: started
enabled: true
scope: user
when:
- inventory_hostname in groups['laptop_anchor']
- ansible_os_family in ['Debian', 'RedHat', 'Archlinux']
- name: Enable daylight agent timer
ansible.builtin.systemd:
name: hermes-laptop-daylight.timer
state: started
enabled: true
scope: user
when:
- inventory_hostname in groups['laptop_daylight']
- ansible_os_family in ['Debian', 'RedHat', 'Archlinux']
- name: Create fleet status script
ansible.builtin.copy:
dest: "{{ timmy_dir }}/scripts/status.sh"
content: |
#!/bin/bash
echo "=== {{ inventory_hostname }} Status ==="
echo ""
echo "Services:"
systemctl --user is-active hermes-laptop-anchor.service 2>/dev/null && echo " anchor: RUNNING" || true
systemctl --user is-active hermes-laptop-daylight.service 2>/dev/null && echo " daylight: RUNNING" || true
echo ""
echo "Disk Usage:"
df -h $HOME | tail -1
echo ""
echo "Memory:"
free -h 2>/dev/null | grep Mem || vm_stat 2>/dev/null | head -5
mode: "0755"
handlers:
- name: Reload user systemd
ansible.builtin.command: systemctl --user daemon-reload
changed_when: true

View File

@@ -0,0 +1,15 @@
[Unit]
Description=Hermes Laptop Anchor Agent (24/7)
After=network.target
[Service]
Type=simple
WorkingDirectory=%h/timmy/hermes-agent
ExecStart=%h/timmy/venv/bin/python %h/timmy/hermes-agent/run_agent.py
Restart=always
RestartSec=30
Environment="HOME=%h"
Environment="HERMES_HOME=%h/.hermes"
[Install]
WantedBy=default.target

View File

@@ -0,0 +1,16 @@
[Unit]
Description=Hermes Laptop Daylight Agent
After=network.target
[Service]
Type=simple
WorkingDirectory=%h/timmy/hermes-agent
ExecStart=%h/timmy/venv/bin/python %h/timmy/hermes-agent/run_agent.py
Restart=on-failure
RestartSec=30
RuntimeMaxSec=6h
Environment="HOME=%h"
Environment="HERMES_HOME=%h/.hermes"
[Install]
WantedBy=default.target

View File

@@ -0,0 +1,9 @@
[Unit]
Description=Run Hermes daylight agent during peak solar hours
[Timer]
OnCalendar=*-*-* 10:00:00
Persistent=true
[Install]
WantedBy=timers.target

View File

@@ -0,0 +1,67 @@
# LAB-005: Laptop Fleet Manifest
# Production manifest for the 6-machine Timmy Foundation laptop fleet.
# Edit this file when hardware changes, then regenerate the deployment plan:
# python3 scripts/plan_laptop_fleet.py configs/laptop-fleet-manifest.yaml --markdown > docs/LAB-005-laptop-fleet-deployment.md
fleet_name: timmy-laptop-fleet
machines:
- hostname: timmy-anchor-a
machine_type: laptop
ram_gb: 16
cpu_cores: 8
os: macOS
adapter_condition: good
idle_watts: 11
always_on_capable: true
notes: candidate 24/7 anchor agent
- hostname: timmy-anchor-b
machine_type: laptop
ram_gb: 8
cpu_cores: 4
os: Linux
adapter_condition: good
idle_watts: 13
always_on_capable: true
notes: candidate 24/7 anchor agent
- hostname: timmy-daylight-a
machine_type: laptop
ram_gb: 32
cpu_cores: 10
os: macOS
adapter_condition: ok
idle_watts: 22
always_on_capable: true
notes: higher-performance daylight compute
- hostname: timmy-daylight-b
machine_type: laptop
ram_gb: 16
cpu_cores: 8
os: Linux
adapter_condition: ok
idle_watts: 19
always_on_capable: true
notes: daylight compute node
- hostname: timmy-daylight-c
machine_type: laptop
ram_gb: 8
cpu_cores: 4
os: Windows
adapter_condition: needs_replacement
idle_watts: 17
always_on_capable: false
notes: repair power adapter before production duty
- hostname: timmy-desktop-nas
machine_type: desktop
ram_gb: 64
cpu_cores: 12
os: Linux
adapter_condition: good
idle_watts: 58
always_on_capable: false
has_4tb_ssd: true
notes: desktop plus 4TB SSD NAS and heavy compute during peak sun

View File

@@ -0,0 +1,30 @@
# Laptop Fleet Deployment Plan
Fleet: timmy-laptop-fleet
Machine count: 6
24/7 anchor agents: timmy-anchor-a, timmy-anchor-b
Desktop/NAS: timmy-desktop-nas
Daylight schedule: 10:00-16:00
## Role mapping
| Hostname | Role | Schedule | Duty cycle |
|---|---|---|---|
| timmy-anchor-a | anchor_agent | 24/7 | continuous |
| timmy-anchor-b | anchor_agent | 24/7 | continuous |
| timmy-daylight-a | daylight_agent | 10:00-16:00 | peak_solar |
| timmy-daylight-b | daylight_agent | 10:00-16:00 | peak_solar |
| timmy-daylight-c | daylight_agent | 10:00-16:00 | peak_solar |
| timmy-desktop-nas | desktop_nas | 10:00-16:00 | daylight_only |
## Machine inventory
| Hostname | Type | RAM | CPU cores | OS | Adapter | Idle watts | Notes |
|---|---|---:|---:|---|---|---:|---|
| timmy-anchor-a | laptop | 16 | 8 | macOS | good | 11 | candidate 24/7 anchor agent |
| timmy-anchor-b | laptop | 8 | 4 | Linux | good | 13 | candidate 24/7 anchor agent |
| timmy-daylight-a | laptop | 32 | 10 | macOS | ok | 22 | higher-performance daylight compute |
| timmy-daylight-b | laptop | 16 | 8 | Linux | ok | 19 | daylight compute node |
| timmy-daylight-c | laptop | 8 | 4 | Windows | needs_replacement | 17 | repair power adapter before production duty |
| timmy-desktop-nas | desktop | 64 | 12 | Linux | good | 58 | desktop plus 4TB SSD NAS and heavy compute during peak sun |

View File

@@ -1,172 +0,0 @@
# Shadow Maths Triage Rubric (MATH-001)
**Status**: Draft v1.0 **Date**: 2026-04-26 **Author**: Timmy
**Milestone**: Contribute to Mathematics — Shadow Maths Search
**Parent**: #876 — [MATH][EPIC] Shadow Maths
---
## Purpose
Timmy's mathematics contribution program targets *bounded, verifiable, useful* problems hiding in plain sight. This rubric operationalizes "shadow maths" — distinguishing legitimate first-crack contributions from crank Grand Unified Theories.
The rubric serves two roles:
1. **Triage gate** — filter submissions and scout list candidates worth pursuing.
2. **No-crank guardrail** — explicitly reject unfalsifiable, unscoped, or unsourced claims.
---
## Candidate Categories (Positive Types)
| Category | Description | Verification Path | Useful Because |
|----------|-------------|-------------------|---------------|
| **Small lemma** | Missing but straightforward piece in an active area (e.g., "Proposition 3.2 in Smith 2021 needs this case analysis") | Check paper + 12 related references; prove or give counterexample | Clarifies existing theory, removes ambiguity |
| **Counterexample search** | Find explicit counterexample to a claimed-but-unproven statement (often from MO/SE) | Compute/construct + cite the original claim | Prevents propagation of errors |
| **Computational classification** | Exhaustive enumeration/classification of a small infinite family (e.g., "all groups of order < 200 with property X") | Code is verifiable; results match known data | Creates reference data, spotlights patterns |
| **Formalization gap** | Statement already believed true but missing from Lean/mathlib/Isabelle | Formal proof artifact; merges to mainline library | Makes mathematics machine-checkable |
| **OEIS sequence note** | New sequence entry or correction to an existing entry with proof/algorithm | OEIS A-number + formula/generation code | Public archival, enables further work |
| **Exposition repair** | Fix an unclear proof, fill a gap, simplify an argument in an existing paper | Side-by-side diff + justification for each change | Improves pedagogy, reduces confusion |
| **MathOverflow-quality answer** | Answer to a specific, bounded, research-level question on MO/SE that has no accepted answer | Cite question + self-contained proof/computation | Serves the community directly |
---
## Rejection Criteria (No-Crank Guardrails)
> Any candidate that triggers one or more of these is **rejected outright** — no scoring needed.
| Rule | What to look for | Why it's crank |
|------|------------------|----------------|
| **Unsourced grand theory** | Claim introduces new "framework"/"paradigm" without citing specific bounded problem it solves | Mathematics advances by solving problems, not proposing frameworks |
| **Impossible scope** | "I will prove/disprove the Riemann Hypothesis", "classify all finite simple groups" | Demonstrably beyond single-attack capability |
| **No verification path** | No way for a third party to check the work (no code, no formalization, no explicit examples) | Cannot be wrong if it cannot be checked |
| **Novelty claim without literature search** | States "I believe this is new" without checking MathSciNet/arXiv/Google Scholar | Almost certainly reinvention or known result |
| **Vague mathematical objects** | Uses undefined or ambiguous terminology ("energy", "resonance", "harmonic" in non-standard ways) | Not mathematics |
| **Secrecy or paywall** | Key definition or proof behind a paywall or withheld | Not sovereign; not verifiable |
| **Symbolic overloading without definition** | Repurposes standard notation in non-standard ways without explicit redefinition | Creates confusion, not clarity |
| **Invariance violations** | Claims "up to isomorphism" or "modulo equivalence" without defining the equivalence relation | Not mathematically precise |
| **Cherry-picked examples as proof** | Proves only easy special cases and claims the general case follows | Example ≠ theorem |
| **Circular citation chains** | Relies on unpublished/preprint work that itself cites the candidate as motivation | Not a foundation |
| **No clear problem statement** | Cannot write a one-sentence problem statement in standard mathematical English | Not a problem; just musings |
| **Claims of "obvious" or "clear" for non-trivial steps** | Uses "obviously" or "it is clear that" where a proof requires >2 lines | Evasion |
| **References only popular science / non-technical sources** | Cites Penrose, Hawking, Tegmark for technical claims | Wrong tier of source |
| **All notation defined in non-standard way** | Redefines basic operators (+, ×, ≤) without explicit warning | Not mathematics |
| **No engagement with existing literature** | Zero citations to relevant peer-reviewed work or established preprints | scholarship was not done |
| **Claims of "disproof" of widely-accepted theorems** | Without finding a peer-reviewed error in the existing proof | Almost certainly wrong |
---
## Evidence Tiers
| Tier | Artifact | What it Proves |
|------|----------|----------------|
| **T3 — Literature** | MathSciNet / Zentralblatt / Google Scholar citations showing the problem is real and open | Problem exists in the literature |
| **T2 — Executable** | Python/Sage/Lean code that others can run to verify computation/formalization | Result is reproducible |
| **T1 — Human-reviewed** | MO answer with upvotes, referee report, or explicit external review | Independent verification |
| **T0 — Self-contained** | Clear statement + proof/computation in a single document, all definitions explicit | Standalone correctness |
A valid candidate must have at least **one** T3 citation (shows the problem is real) AND a verification artifact (T0 minimum; T2 ideal).
---
## Scoring Rubric
Score each candidate on **4 dimensions**, each 03. Maximum 12 points.
| Dimension | 3 (excellent) | 2 (good) | 1 (minimal) | 0 (absent) |
|-----------|---------------|----------|-------------|------------|
| **Boundedness** | Scope is explicitly finite/small (single lemma, finite classification < N, one SE question) | Scope is implied bounded but not quantified | Scope is large/vague but attackable | Unbounded or impossible scope |
| **Verifiability** | T2 artifact (code/formalization) + T3 citation | T0 proof + T3 citation | Proof/computation only, no citations | No way to check independently |
| **Usefulness** | Solves problem others actively need (cites known difficulty, fills formalization gap) | Solves a clean exercise or interesting special case | Interesting but no clear audience | Pointless or self-referential |
| **Discipline** | No crank flags; explicit rejection criteria cleanly passed | Minor crank flags (vague wording) but overall sound | Some crank flags but bounded scope rescues it | Triggers multiple rejection rules |
**Thresholds**:
- **812**: Legitimate shadow maths candidate — queue for work
- **47**: Needs refinement — reject unless strong disciplinary context
- **03**: Reject as crank / out-of-scope
---
## Three Worked Examples
### Example 1: Small Lemma — Bounded
**Candidate**: "Proposition 3.2 in 'Coarse Geometry and Coarse Embeddings' (Lang-Schlichenmaier 2005) states that every finite CW-complex has Markov property. The proof gives 'it follows by induction on skeleta' without handling the attaching map case. Fill the gap."
**Triage**:
- **Category**: Small lemma (exposition repair + proof gap fill)
- **Boundedness**: 3 — single proposition in a specific paper, 23 pages max
- **Verifiability**: 3 — paper is cited (T3), self-contained proof in 20 lines (T0), can formalize in Lean (T2 possible)
- **Usefulness**: 3 — readers of this paper hit this gap; Lean formalization needed for mathlib
- **Discipline**: 3 — no crank flags; scoped, sourced, technical
- **Total**: **12/12** → YES
**Action**: File ticket "MATH-LEMMA-001"; assign to formalization lane + human review.
---
### Example 2: Grand Unified Theory — CRANK
**Candidate**: "I have discovered the Energy-Conscious Riemann Hypothesis framework. The zeros of ζ(s) correspond to harmonic resonance frequencies in prime-number energy manifolds. Uses my new Operator-Weight theory."
**Triage**:
- **Category**: N/A
- **Rejection triggers**:
- ✗ Unsourced grand theory (introduces "Energy-Conscious", "Operator-Weight" with no definition in standard math)
- ✗ No verification path (no computation, no reference to known data)
- ✗ No literature engagement (zero citations)
- ✗ Vague mathematical objects ("energy", "resonance", "harmonic")
- ✗ Claims new framework
- **Score**: 0 — **REJECT**
**Action**: Close with reason "crank: unsourced grand theory + no verification path".
---
### Example 3: Computational Classification — Bounded
**Candidate**: "Compute all 3-headed Turing machines with 3 states that halt within 100 steps on the blank tape. There are 9 such machines. This fills an OEIS gap: A327000 only lists up to 2-state 2-symbol."
**Triage**:
- **Category**: Computational classification + OEIS sequence
- **Boundedness**: 3 — finite exhaustive enumeration (3^6 = 729 machines, filter to 9)
- **Verifiability**: 2 — code is executable (T2), but no T3 citation of why this sequence matters yet
- **Usefulness**: 2 — plugs a gap in the Busy Beaver frontier; OEIS entry gets concrete data
- **Discipline**: 3 — explicit scope, reproducible, submits to OEIS (external review path)
- **Total**: **10/12** → YES (minor fix: add motivation/references)
**Action**: Accept; write exhaustive script; submit OEIS draft with code + results; file MATH-COMP-001.
---
## Operational Use
### Triage Workflow
1. **Read candidate** (issue, email, self-generated idea).
2. **Check rejection criteria first** — if any trigger → **REJECT** immediately, cite rule.
3. If passes rejection gate, **score 4 dimensions**.
4. **Score ≥8** → mark as `shadow-maths-candidate`, route to appropriate lane:
- Lemma/exposition → `formalization-lane`
- Computation → `compute-lane`
- MO/SE answer → `answer-lane`
- OEIS → `oeis-lane`
5. **Score 47** → requires refinement; ask for:
- Explicit scope bound
- T3 citation
- Verification artifact
6. **Score ≤3** → reject with specific rule(s) triggered.
### Guardrail Enforcement
The following prompts/agents **must refuse** to work on any candidate that:
- Triggers any rejection criterion (before any code/proof work)
- Has no T3 citation (real problem statement from literature)
- Has no bounded scope (cannot write ≤1-sentence problem statement)
Enforcement is a **pre-flight check** in the task intake pipeline.
---
## Revision History
- v1.0 — 2026-04-26 — initial rubric + 3 scored examples

View File

@@ -50,3 +50,43 @@ def test_manifest_template_is_valid_yaml() -> None:
data = yaml.safe_load(Path("docs/laptop-fleet-manifest.example.yaml").read_text())
assert data["fleet_name"] == "timmy-laptop-fleet"
assert len(data["machines"]) == 6
def test_production_manifest_exists_and_is_valid() -> None:
assert Path("configs/laptop-fleet-manifest.yaml").exists()
data = yaml.safe_load(Path("configs/laptop-fleet-manifest.yaml").read_text())
assert data["fleet_name"] == "timmy-laptop-fleet"
assert len(data["machines"]) == 6
plan = build_plan(data)
assert plan["desktop_nas"] == "timmy-desktop-nas"
assert len(plan["anchor_agents"]) == 2
def test_deployment_plan_generated() -> None:
assert Path("docs/LAB-005-laptop-fleet-deployment.md").exists()
content = Path("docs/LAB-005-laptop-fleet-deployment.md").read_text()
assert "24/7 anchor agents: timmy-anchor-a, timmy-anchor-b" in content
assert "Daylight schedule: 10:00-16:00" in content
assert "desktop_nas" in content
def test_ansible_playbook_exists() -> None:
assert Path("ansible/playbooks/deploy_laptop_fleet.yml").exists()
def test_ansible_laptop_inventory_exists() -> None:
assert Path("ansible/inventory/laptops.ini").exists()
content = Path("ansible/inventory/laptops.ini").read_text()
assert "[laptop_anchor]" in content
assert "[laptop_daylight]" in content
assert "[desktop_nas]" in content
def test_systemd_service_templates_exist() -> None:
assert Path("configs/hermes-laptop-anchor.service").exists()
assert Path("configs/hermes-laptop-daylight.service").exists()
assert Path("configs/hermes-laptop-daylight.timer").exists()
anchor = Path("configs/hermes-laptop-anchor.service").read_text()
daylight = Path("configs/hermes-laptop-daylight.service").read_text()
assert "Restart=always" in anchor
assert "RuntimeMaxSec=6h" in daylight