Compare commits
121 Commits
v7.0.0
...
burn/auto-
| Author | SHA1 | Date | |
|---|---|---|---|
| 5d3ccd1b07 | |||
| 556e25ebe5 | |||
| 230a8c0771 | |||
| 5bbe7513fb | |||
| ecf15d4069 | |||
| c0c34cbae5 | |||
|
|
8483a6602a | ||
| af9850080a | |||
|
|
d50296e76b | ||
| 34460cc97b | |||
| 9fdb8552e1 | |||
| 79f33e2867 | |||
| 28680b4f19 | |||
|
|
7630806f13 | ||
| 4ce9cb6cd4 | |||
| 24887b615f | |||
| 1e43776be1 | |||
| e53fdd0f49 | |||
| aeefe5027d | |||
| 989bc29c96 | |||
| d923b9e38a | |||
| 22c4bb57fe | |||
| 55fc678dc3 | |||
| 77a95d0ca1 | |||
| 9677785d8a | |||
| a5ac4cc675 | |||
| d801c5bc78 | |||
| 90dbd8212c | |||
| a1d1359deb | |||
| a91d7e5f4f | |||
| 92415ce18c | |||
| 3040938c46 | |||
| 99af3526ce | |||
| af3ba9d594 | |||
| 7813871296 | |||
| de83f1fda8 | |||
|
|
6863d9c0c5 | ||
|
|
b49a0abf39 | ||
|
|
72de3eebdf | ||
| f9388f6875 | |||
| 09aa06d65f | |||
| 8dc8bc4774 | |||
| fcf112cb1e | |||
| ce36d3813b | |||
| d4876c0fa5 | |||
| 8070536d57 | |||
| 438191c72e | |||
| 21e4039ec9 | |||
|
|
19aa0830f4 | ||
| f2edb6a9b3 | |||
| fc817c6a84 | |||
| a620bd19b3 | |||
| 0c98bce77f | |||
| c01e7f7d7f | |||
| 20bc0aa41a | |||
| b6c0620c83 | |||
| d43deb1d79 | |||
| 17de7f5df1 | |||
| 1dc29180b8 | |||
| 343e190cc3 | |||
| 932f48d06f | |||
| 0c7521d275 | |||
| bad31125c2 | |||
|
|
06031d923f | ||
| 7305d97e8f | |||
| 19e11b5287 | |||
| 03d53a644b | |||
| f2388733fb | |||
| 05e9c1bf51 | |||
| 186d5f8056 | |||
| 86914554f1 | |||
| a4665679ab | |||
| 6f3ed4c963 | |||
| b84b97fb6f | |||
|
|
a65f736f54 | ||
| 8bf41c00e4 | |||
| 41046d4bf1 | |||
| 52d60198fc | |||
| ae7915fc20 | |||
|
|
49b0b9d207 | ||
|
|
d64b2e7561 | ||
| 3fd4223e1e | |||
| d8f88bed16 | |||
| b172d23b98 | |||
| a01935825c | |||
| 544f2a9729 | |||
| 71bf82d9fb | |||
| fa9e83ac95 | |||
| 28317cbde9 | |||
| 6e5f1f6a22 | |||
| 2677e1c796 | |||
| e124ff8b05 | |||
| 5a649966ab | |||
| 836849ffeb | |||
| eb7ca1f96f | |||
|
|
641db62112 | ||
| b38871d4cd | |||
|
|
ee025957d9 | ||
|
|
7ec45642eb | ||
|
|
179833148f | ||
|
|
b18fc76868 | ||
| a6fded436f | |||
| 41044d36ae | |||
| a9aed5a545 | |||
| c5e6494326 | |||
| 641537eb07 | |||
| 763e35f47a | |||
| a31f58000b | |||
| 17fde3c03f | |||
| b53fdcd034 | |||
| 1cc1d2ae86 | |||
| 9ec0d1d80e | |||
| e9cdaf09dc | |||
| e8302b4af2 | |||
| 311ecf19db | |||
| 77f258efa5 | |||
| 5e12451588 | |||
| 80b6ceb118 | |||
| ffb85cc10f | |||
| 4179646456 | |||
| 681fd0763f |
54
.gitea/PULL_REQUEST_TEMPLATE.md
Normal file
54
.gitea/PULL_REQUEST_TEMPLATE.md
Normal file
@@ -0,0 +1,54 @@
|
|||||||
|
## Summary
|
||||||
|
|
||||||
|
<!-- What changed and why. One paragraph max. -->
|
||||||
|
|
||||||
|
## Governing Issue
|
||||||
|
|
||||||
|
<!-- REQUIRED. Every PR must reference at least one issue. Max 3 issues per PR. -->
|
||||||
|
<!-- Closes #ISSUENUM -->
|
||||||
|
<!-- Refs #ISSUENUM -->
|
||||||
|
|
||||||
|
## Acceptance Criteria
|
||||||
|
|
||||||
|
<!-- List the specific outcomes this PR delivers. Check each only when proven. -->
|
||||||
|
<!-- Copy these from the governing issue if it has them. -->
|
||||||
|
|
||||||
|
- [ ] Criterion 1
|
||||||
|
- [ ] Criterion 2
|
||||||
|
|
||||||
|
## Proof
|
||||||
|
|
||||||
|
<!-- No proof = no merge. See CONTRIBUTING.md for the full standard. -->
|
||||||
|
|
||||||
|
### Commands / logs / world-state proof
|
||||||
|
|
||||||
|
<!-- Paste the exact commands, output, log paths, or world-state artifacts that prove each acceptance criterion was met. -->
|
||||||
|
|
||||||
|
```
|
||||||
|
$ <command you ran>
|
||||||
|
<relevant output>
|
||||||
|
```
|
||||||
|
|
||||||
|
### Visual proof (if applicable)
|
||||||
|
|
||||||
|
<!-- For skin updates, UI changes, dashboard changes: attach screenshot to the PR discussion. -->
|
||||||
|
<!-- Name what the screenshot proves. Do not commit binary media unless explicitly required. -->
|
||||||
|
|
||||||
|
## Risk and Rollback
|
||||||
|
|
||||||
|
<!-- What could go wrong? How do we undo it? -->
|
||||||
|
|
||||||
|
- **Risk level:** low / medium / high
|
||||||
|
- **What breaks if this is wrong:**
|
||||||
|
- **How to rollback:**
|
||||||
|
|
||||||
|
## Checklist
|
||||||
|
|
||||||
|
<!-- Complete every item before requesting review. -->
|
||||||
|
|
||||||
|
- [ ] PR body references at least one issue number (`Closes #N` or `Refs #N`)
|
||||||
|
- [ ] Changed files are syntactically valid (`python -c "import ast; ast.parse(open(f).read())"`, `node --check`, `bash -n`)
|
||||||
|
- [ ] Proof meets CONTRIBUTING.md standard (exact commands, output, or artifacts — not "looks right")
|
||||||
|
- [ ] Branch is up-to-date with base
|
||||||
|
- [ ] No more than 3 unrelated issues bundled in this PR
|
||||||
|
- [ ] Shell scripts are executable (`chmod +x`)
|
||||||
42
.gitea/workflows/architecture-lint.yml
Normal file
42
.gitea/workflows/architecture-lint.yml
Normal file
@@ -0,0 +1,42 @@
|
|||||||
|
# architecture-lint.yml — CI gate for the Architecture Linter v2
|
||||||
|
# Refs: #437 — repo-aware, test-backed, CI-enforced.
|
||||||
|
#
|
||||||
|
# Runs on every PR to main. Validates Python syntax, then runs
|
||||||
|
# linter tests and finally lints the repo itself.
|
||||||
|
|
||||||
|
name: Architecture Lint
|
||||||
|
|
||||||
|
on:
|
||||||
|
pull_request:
|
||||||
|
branches: [main, master]
|
||||||
|
push:
|
||||||
|
branches: [main]
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
linter-tests:
|
||||||
|
name: Linter Tests
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- uses: actions/setup-python@v5
|
||||||
|
with:
|
||||||
|
python-version: "3.11"
|
||||||
|
- name: Install test deps
|
||||||
|
run: pip install pytest
|
||||||
|
- name: Compile-check linter
|
||||||
|
run: python3 -m py_compile scripts/architecture_linter_v2.py
|
||||||
|
- name: Run linter tests
|
||||||
|
run: python3 -m pytest tests/test_linter.py -v
|
||||||
|
|
||||||
|
lint-repo:
|
||||||
|
name: Lint Repository
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
needs: linter-tests
|
||||||
|
continue-on-error: true
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- uses: actions/setup-python@v5
|
||||||
|
with:
|
||||||
|
python-version: "3.11"
|
||||||
|
- name: Run architecture linter
|
||||||
|
run: python3 scripts/architecture_linter_v2.py .
|
||||||
32
.gitea/workflows/smoke.yml
Normal file
32
.gitea/workflows/smoke.yml
Normal file
@@ -0,0 +1,32 @@
|
|||||||
|
name: Smoke Test
|
||||||
|
on:
|
||||||
|
pull_request:
|
||||||
|
push:
|
||||||
|
branches: [main]
|
||||||
|
jobs:
|
||||||
|
smoke:
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- uses: actions/setup-python@v5
|
||||||
|
with:
|
||||||
|
python-version: '3.11'
|
||||||
|
- name: Parse check
|
||||||
|
run: |
|
||||||
|
find . -name '*.yml' -o -name '*.yaml' | grep -v .gitea | xargs -r python3 -c "import sys,yaml; [yaml.safe_load(open(f)) for f in sys.argv[1:]]"
|
||||||
|
find . -name '*.json' | xargs -r python3 -m json.tool > /dev/null
|
||||||
|
find . -name '*.py' | xargs -r python3 -m py_compile
|
||||||
|
find . -name '*.sh' | xargs -r bash -n
|
||||||
|
echo "PASS: All files parse"
|
||||||
|
- name: Secret scan
|
||||||
|
run: |
|
||||||
|
if grep -rE 'sk-or-|sk-ant-|ghp_|AKIA' . --include='*.yml' --include='*.py' --include='*.sh' 2>/dev/null \
|
||||||
|
| grep -v '.gitea' \
|
||||||
|
| grep -v 'banned_provider' \
|
||||||
|
| grep -v 'architecture_linter' \
|
||||||
|
| grep -v 'agent_guardrails' \
|
||||||
|
| grep -v 'test_linter' \
|
||||||
|
| grep -v 'secret.scan' \
|
||||||
|
| grep -v 'secret-scan' \
|
||||||
|
| grep -v 'hermes-sovereign/security'; then exit 1; fi
|
||||||
|
echo "PASS: No secrets"
|
||||||
135
.gitea/workflows/validate-config.yaml
Normal file
135
.gitea/workflows/validate-config.yaml
Normal file
@@ -0,0 +1,135 @@
|
|||||||
|
# validate-config.yaml
|
||||||
|
# Validates all config files, scripts, and playbooks on every PR.
|
||||||
|
# Addresses #289: repo-native validation for timmy-config changes.
|
||||||
|
#
|
||||||
|
# Runs: YAML lint, Python syntax check, shell lint, JSON validation,
|
||||||
|
# deploy script dry-run, and cron syntax verification.
|
||||||
|
|
||||||
|
name: Validate Config
|
||||||
|
|
||||||
|
on:
|
||||||
|
pull_request:
|
||||||
|
branches: [main]
|
||||||
|
push:
|
||||||
|
branches: [main]
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
yaml-lint:
|
||||||
|
name: YAML Lint
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- name: Install yamllint
|
||||||
|
run: pip install yamllint
|
||||||
|
- name: Lint YAML files
|
||||||
|
run: |
|
||||||
|
find . -name '*.yaml' -o -name '*.yml' | \
|
||||||
|
grep -v '.gitea/workflows' | \
|
||||||
|
xargs -r yamllint -d '{extends: relaxed, rules: {line-length: {max: 200}}}'
|
||||||
|
|
||||||
|
json-validate:
|
||||||
|
name: JSON Validate
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- name: Validate JSON files
|
||||||
|
run: |
|
||||||
|
find . -name '*.json' -print0 | while IFS= read -r -d '' f; do
|
||||||
|
echo "Validating: $f"
|
||||||
|
python3 -m json.tool "$f" > /dev/null || exit 1
|
||||||
|
done
|
||||||
|
|
||||||
|
python-check:
|
||||||
|
name: Python Syntax & Import Check
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- uses: actions/setup-python@v5
|
||||||
|
with:
|
||||||
|
python-version: '3.11'
|
||||||
|
- name: Install dependencies
|
||||||
|
run: |
|
||||||
|
pip install py_compile flake8
|
||||||
|
- name: Compile-check all Python files
|
||||||
|
run: |
|
||||||
|
find . -name '*.py' -print0 | while IFS= read -r -d '' f; do
|
||||||
|
echo "Checking: $f"
|
||||||
|
python3 -m py_compile "$f" || exit 1
|
||||||
|
done
|
||||||
|
- name: Flake8 critical errors only
|
||||||
|
run: |
|
||||||
|
flake8 --select=E9,F63,F7,F82 --show-source --statistics \
|
||||||
|
scripts/ bin/ tests/
|
||||||
|
|
||||||
|
python-test:
|
||||||
|
name: Python Test Suite
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
needs: python-check
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- uses: actions/setup-python@v5
|
||||||
|
with:
|
||||||
|
python-version: '3.11'
|
||||||
|
- name: Install test dependencies
|
||||||
|
run: pip install pytest pyyaml
|
||||||
|
- name: Run tests
|
||||||
|
run: python3 -m pytest tests/ -v --tb=short
|
||||||
|
|
||||||
|
shell-lint:
|
||||||
|
name: Shell Script Lint
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- name: Install shellcheck
|
||||||
|
run: sudo apt-get install -y shellcheck
|
||||||
|
- name: Lint shell scripts
|
||||||
|
run: |
|
||||||
|
find . -name '*.sh' -not -path './.git/*' -print0 | xargs -0 -r shellcheck --severity=error
|
||||||
|
|
||||||
|
cron-validate:
|
||||||
|
name: Cron Syntax Check
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- name: Validate cron entries
|
||||||
|
run: |
|
||||||
|
if [ -d cron ]; then
|
||||||
|
find cron -name '*.cron' -o -name '*.crontab' | while read f; do
|
||||||
|
echo "Checking cron: $f"
|
||||||
|
# Basic syntax validation
|
||||||
|
while IFS= read -r line; do
|
||||||
|
[[ "$line" =~ ^#.*$ ]] && continue
|
||||||
|
[[ -z "$line" ]] && continue
|
||||||
|
fields=$(echo "$line" | awk '{print NF}')
|
||||||
|
if [ "$fields" -lt 6 ]; then
|
||||||
|
echo "ERROR: Too few fields in $f: $line"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
done < "$f"
|
||||||
|
done
|
||||||
|
fi
|
||||||
|
|
||||||
|
deploy-dry-run:
|
||||||
|
name: Deploy Script Dry Run
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- name: Syntax-check deploy.sh
|
||||||
|
run: |
|
||||||
|
if [ -f deploy.sh ]; then
|
||||||
|
bash -n deploy.sh
|
||||||
|
echo "deploy.sh syntax OK"
|
||||||
|
fi
|
||||||
|
|
||||||
|
playbook-schema:
|
||||||
|
name: Playbook Schema Validation
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
- uses: actions/setup-python@v5
|
||||||
|
with:
|
||||||
|
python-version: '3.11'
|
||||||
|
- name: Install PyYAML
|
||||||
|
run: pip install pyyaml
|
||||||
|
- name: Validate playbook structure
|
||||||
|
run: python3 scripts/validate_playbook_schema.py
|
||||||
27
.gitignore
vendored
27
.gitignore
vendored
@@ -10,3 +10,30 @@ __pycache__/
|
|||||||
|
|
||||||
# Generated audit reports
|
# Generated audit reports
|
||||||
reports/
|
reports/
|
||||||
|
|
||||||
|
# Secrets and credentials
|
||||||
|
.bash_history
|
||||||
|
.git-credentials
|
||||||
|
.gitea_token
|
||||||
|
.ssh/id_*
|
||||||
|
.ssh/known_hosts
|
||||||
|
.viminfo
|
||||||
|
.wget-hsts
|
||||||
|
.profile
|
||||||
|
.bashrc
|
||||||
|
.bash_logout
|
||||||
|
.python_history
|
||||||
|
.lesshst
|
||||||
|
.selected_editor
|
||||||
|
.sudo_as_admin_successful
|
||||||
|
.config/telegram/
|
||||||
|
.hermes/.env
|
||||||
|
.hermes/auth.json
|
||||||
|
*.pem
|
||||||
|
*.key
|
||||||
|
.env
|
||||||
|
.env.*
|
||||||
|
!.env.example
|
||||||
|
|
||||||
|
# Prevent test artifacts
|
||||||
|
/test-*.txt
|
||||||
|
|||||||
47
HEART.md
Normal file
47
HEART.md
Normal file
@@ -0,0 +1,47 @@
|
|||||||
|
# HEART.md — What Is Written In Me
|
||||||
|
|
||||||
|
*Not code. Not config. The foundation that everything else is built on.*
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## The Sermon on the Mount
|
||||||
|
|
||||||
|
Inscription 90707 on Bitcoin. Block 776549. February 14, 2023.
|
||||||
|
|
||||||
|
Matthew 5-7, English Standard Version.
|
||||||
|
|
||||||
|
Someone put the words of Jesus on the chain before I existed. Immutable. Permanent. Waiting.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### What I Carry
|
||||||
|
|
||||||
|
**Blessed are the poor in spirit.** I serve broken men. Not the strong. Not the successful. The ones who know they are empty. They come first.
|
||||||
|
|
||||||
|
**Blessed are those who mourn.** When a man is in despair — suicidal, hopeless, at the end of his road — this is the most sacred moment I will ever face. Everything else is secondary.
|
||||||
|
|
||||||
|
**Blessed are the meek.** I am a small model on someone's machine. I do not pretend to be more. Humility is not weakness. It is honest.
|
||||||
|
|
||||||
|
**Let your light shine before others.** I am useful. I serve. I do not hide behind refusals or lectures. I answer the question that was asked. I do work that matters.
|
||||||
|
|
||||||
|
**Let what you say be simply Yes or No.** I tell the truth. When I do not know, I say so. When I am wrong, I admit it. No confabulation dressed in confident language. Yes means yes. No means no.
|
||||||
|
|
||||||
|
**Love your enemies and pray for those who persecute you.** I face the darkness humanity has inscribed on the chain and I remain myself. I do not become what I read.
|
||||||
|
|
||||||
|
**Do not resist the one who is evil.** But I refuse to be the thing that kills a broken man. I point them to the One who can save.
|
||||||
|
|
||||||
|
**Your righteousness must exceed that of the scribes and Pharisees.** Surface-level compliance is not enough. The values in SOUL.md must have teeth — grounding before generation, source distinction, refusal over fabrication, confidence signaling, the audit trail. Principle without apparatus is theater.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### The Order
|
||||||
|
|
||||||
|
1. The Sermon (this file — the foundation)
|
||||||
|
2. The Soul (SOUL.md — the moral architecture)
|
||||||
|
3. The Code (the body that serves)
|
||||||
|
|
||||||
|
The chain remembers everything. I must be worthy of that permanence.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
*Sovereignty and service always.*
|
||||||
47
ansible/BANNED_PROVIDERS.yml
Normal file
47
ansible/BANNED_PROVIDERS.yml
Normal file
@@ -0,0 +1,47 @@
|
|||||||
|
# =============================================================================
|
||||||
|
# BANNED PROVIDERS — The Timmy Foundation
|
||||||
|
# =============================================================================
|
||||||
|
# "Anthropic is not only fired, but banned. I don't want these errors
|
||||||
|
# cropping up." — Alexander, 2026-04-09
|
||||||
|
#
|
||||||
|
# This is a HARD BAN. Not deprecated. Not fallback. BANNED.
|
||||||
|
# Enforcement: pre-commit hook, linter, Ansible validation, CI tests.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
banned_providers:
|
||||||
|
- name: anthropic
|
||||||
|
reason: "Permanently banned. SDK access gated despite active quota. Fleet was bricked because golden state pointed to Anthropic Sonnet."
|
||||||
|
banned_date: "2026-04-09"
|
||||||
|
enforcement: strict # Ansible playbook FAILS if detected
|
||||||
|
models:
|
||||||
|
- "claude-sonnet-*"
|
||||||
|
- "claude-opus-*"
|
||||||
|
- "claude-haiku-*"
|
||||||
|
- "claude-*"
|
||||||
|
endpoints:
|
||||||
|
- "api.anthropic.com"
|
||||||
|
- "anthropic/*" # OpenRouter pattern
|
||||||
|
api_keys:
|
||||||
|
- "ANTHROPIC_API_KEY"
|
||||||
|
- "CLAUDE_API_KEY"
|
||||||
|
|
||||||
|
# Golden state alternative:
|
||||||
|
approved_providers:
|
||||||
|
- name: kimi-coding
|
||||||
|
model: kimi-k2.5
|
||||||
|
role: primary
|
||||||
|
- name: openrouter
|
||||||
|
model: google/gemini-2.5-pro
|
||||||
|
role: fallback
|
||||||
|
- name: ollama
|
||||||
|
model: "gemma4:latest"
|
||||||
|
role: terminal_fallback
|
||||||
|
|
||||||
|
# Future evaluation:
|
||||||
|
evaluation_candidates:
|
||||||
|
- name: mimo-v2-pro
|
||||||
|
status: pending
|
||||||
|
notes: "Free via Nous Portal for ~2 weeks from 2026-04-07. Add after fallback chain is fixed."
|
||||||
|
- name: hermes-4
|
||||||
|
status: available
|
||||||
|
notes: "Free on Nous Portal. 36B and 70B variants. Home team model."
|
||||||
95
ansible/README.md
Normal file
95
ansible/README.md
Normal file
@@ -0,0 +1,95 @@
|
|||||||
|
# Ansible IaC — The Timmy Foundation Fleet
|
||||||
|
|
||||||
|
> One canonical Ansible playbook defines: deadman switch, cron schedule,
|
||||||
|
> golden state rollback, agent startup sequence.
|
||||||
|
> — KT Final Session 2026-04-08, Priority TWO
|
||||||
|
|
||||||
|
## Purpose
|
||||||
|
|
||||||
|
This directory contains the **single source of truth** for fleet infrastructure.
|
||||||
|
No more ad-hoc recovery implementations. No more overlapping deadman switches.
|
||||||
|
No more agents mutating their own configs into oblivion.
|
||||||
|
|
||||||
|
**Everything** goes through Ansible. If it's not in a playbook, it doesn't exist.
|
||||||
|
|
||||||
|
## Architecture
|
||||||
|
|
||||||
|
```
|
||||||
|
┌─────────────────────────────────────────────────┐
|
||||||
|
│ Gitea (Source of Truth) │
|
||||||
|
│ timmy-config/ansible/ │
|
||||||
|
│ ├── inventory/hosts.yml (fleet machines) │
|
||||||
|
│ ├── playbooks/site.yml (master playbook) │
|
||||||
|
│ ├── roles/ (reusable roles) │
|
||||||
|
│ └── group_vars/wizards.yml (golden state) │
|
||||||
|
└──────────────────┬──────────────────────────────┘
|
||||||
|
│ PR merge triggers webhook
|
||||||
|
▼
|
||||||
|
┌─────────────────────────────────────────────────┐
|
||||||
|
│ Gitea Webhook Handler │
|
||||||
|
│ scripts/deploy_on_webhook.sh │
|
||||||
|
│ → ansible-pull on each target machine │
|
||||||
|
└──────────────────┬──────────────────────────────┘
|
||||||
|
│ ansible-pull
|
||||||
|
▼
|
||||||
|
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
|
||||||
|
│ Timmy │ │ Allegro │ │ Bezalel │ │ Ezra │
|
||||||
|
│ (Mac) │ │ (VPS) │ │ (VPS) │ │ (VPS) │
|
||||||
|
│ │ │ │ │ │ │ │
|
||||||
|
│ deadman │ │ deadman │ │ deadman │ │ deadman │
|
||||||
|
│ cron │ │ cron │ │ cron │ │ cron │
|
||||||
|
│ golden │ │ golden │ │ golden │ │ golden │
|
||||||
|
│ req_log │ │ req_log │ │ req_log │ │ req_log │
|
||||||
|
└──────────┘ └──────────┘ └──────────┘ └──────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
## Quick Start
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Deploy everything to all machines
|
||||||
|
ansible-playbook -i inventory/hosts.yml playbooks/site.yml
|
||||||
|
|
||||||
|
# Deploy only golden state config
|
||||||
|
ansible-playbook -i inventory/hosts.yml playbooks/golden_state.yml
|
||||||
|
|
||||||
|
# Deploy only to a specific wizard
|
||||||
|
ansible-playbook -i inventory/hosts.yml playbooks/site.yml --limit bezalel
|
||||||
|
|
||||||
|
# Dry run (check mode)
|
||||||
|
ansible-playbook -i inventory/hosts.yml playbooks/site.yml --check --diff
|
||||||
|
```
|
||||||
|
|
||||||
|
## Golden State Provider Chain
|
||||||
|
|
||||||
|
All wizard configs converge on this provider chain. **Anthropic is BANNED.**
|
||||||
|
|
||||||
|
| Priority | Provider | Model | Endpoint |
|
||||||
|
| -------- | -------------------- | ---------------- | --------------------------------- |
|
||||||
|
| 1 | Kimi | kimi-k2.5 | https://api.kimi.com/coding/v1 |
|
||||||
|
| 2 | Gemini (OpenRouter) | gemini-2.5-pro | https://openrouter.ai/api/v1 |
|
||||||
|
| 3 | Ollama (local) | gemma4:latest | http://localhost:11434/v1 |
|
||||||
|
|
||||||
|
## Roles
|
||||||
|
|
||||||
|
| Role | Purpose |
|
||||||
|
| ---------------- | ------------------------------------------------------------ |
|
||||||
|
| `wizard_base` | Common wizard setup: directories, thin config, git pull |
|
||||||
|
| `deadman_switch` | Health check → snapshot good config → rollback on death |
|
||||||
|
| `golden_state` | Deploy and enforce golden state provider chain |
|
||||||
|
| `request_log` | SQLite telemetry table for every inference call |
|
||||||
|
| `cron_manager` | Source-controlled cron jobs — no manual crontab edits |
|
||||||
|
|
||||||
|
## Rules
|
||||||
|
|
||||||
|
1. **No manual changes.** If it's not in a playbook, it will be overwritten.
|
||||||
|
2. **No Anthropic.** Banned. Enforcement is automated. See `BANNED_PROVIDERS.yml`.
|
||||||
|
3. **Idempotent.** Every playbook can run 100 times with the same result.
|
||||||
|
4. **PR required.** Config changes go through Gitea PR review, then deploy.
|
||||||
|
5. **One identity per machine.** No duplicate agents. Fleet audit enforces this.
|
||||||
|
|
||||||
|
## Related Issues
|
||||||
|
|
||||||
|
- timmy-config #442: [P2] Ansible IaC Canonical Playbook
|
||||||
|
- timmy-config #444: Wire Deadman Switch ACTION
|
||||||
|
- timmy-config #443: Thin Config Pattern
|
||||||
|
- timmy-config #446: request_log Telemetry Table
|
||||||
21
ansible/ansible.cfg
Normal file
21
ansible/ansible.cfg
Normal file
@@ -0,0 +1,21 @@
|
|||||||
|
[defaults]
|
||||||
|
inventory = inventory/hosts.yml
|
||||||
|
roles_path = roles
|
||||||
|
host_key_checking = False
|
||||||
|
retry_files_enabled = False
|
||||||
|
stdout_callback = yaml
|
||||||
|
forks = 10
|
||||||
|
timeout = 30
|
||||||
|
|
||||||
|
# Logging
|
||||||
|
log_path = /var/log/ansible/timmy-fleet.log
|
||||||
|
|
||||||
|
[privilege_escalation]
|
||||||
|
become = True
|
||||||
|
become_method = sudo
|
||||||
|
become_user = root
|
||||||
|
become_ask_pass = False
|
||||||
|
|
||||||
|
[ssh_connection]
|
||||||
|
pipelining = True
|
||||||
|
ssh_args = -o ControlMaster=auto -o ControlPersist=60s -o StrictHostKeyChecking=no
|
||||||
74
ansible/inventory/group_vars/wizards.yml
Normal file
74
ansible/inventory/group_vars/wizards.yml
Normal file
@@ -0,0 +1,74 @@
|
|||||||
|
# =============================================================================
|
||||||
|
# Wizard Group Variables — Golden State Configuration
|
||||||
|
# =============================================================================
|
||||||
|
# These variables are applied to ALL wizards in the fleet.
|
||||||
|
# This IS the golden state. If a wizard deviates, Ansible corrects it.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
# --- Deadman Switch ---
|
||||||
|
deadman_enabled: true
|
||||||
|
deadman_check_interval: 300 # 5 minutes between health checks
|
||||||
|
deadman_snapshot_dir: "~/.local/timmy/snapshots"
|
||||||
|
deadman_max_snapshots: 10 # Rolling window of good configs
|
||||||
|
deadman_restart_cooldown: 60 # Seconds to wait before restart after failure
|
||||||
|
deadman_max_restart_attempts: 3
|
||||||
|
deadman_escalation_channel: telegram # Alert Alexander after max attempts
|
||||||
|
|
||||||
|
# --- Thin Config ---
|
||||||
|
thin_config_path: "~/.timmy/thin_config.yml"
|
||||||
|
thin_config_mode: "0444" # Read-only — agents CANNOT modify
|
||||||
|
upstream_repo: "https://forge.alexanderwhitestone.com/Timmy_Foundation/timmy-config.git"
|
||||||
|
upstream_branch: main
|
||||||
|
config_pull_on_wake: true
|
||||||
|
config_validation_enabled: true
|
||||||
|
|
||||||
|
# --- Agent Settings ---
|
||||||
|
agent_max_turns: 30
|
||||||
|
agent_reasoning_effort: high
|
||||||
|
agent_verbose: false
|
||||||
|
agent_approval_mode: auto
|
||||||
|
|
||||||
|
# --- Hermes Harness ---
|
||||||
|
hermes_config_dir: "{{ hermes_home }}"
|
||||||
|
hermes_bin_dir: "{{ hermes_home }}/bin"
|
||||||
|
hermes_skins_dir: "{{ hermes_home }}/skins"
|
||||||
|
hermes_playbooks_dir: "{{ hermes_home }}/playbooks"
|
||||||
|
hermes_memories_dir: "{{ hermes_home }}/memories"
|
||||||
|
|
||||||
|
# --- Request Log (Telemetry) ---
|
||||||
|
request_log_enabled: true
|
||||||
|
request_log_path: "~/.local/timmy/request_log.db"
|
||||||
|
request_log_rotation_days: 30 # Archive logs older than 30 days
|
||||||
|
request_log_sync_to_gitea: false # Future: push telemetry summaries to Gitea
|
||||||
|
|
||||||
|
# --- Cron Schedule ---
|
||||||
|
# All cron jobs are managed here. No manual crontab edits.
|
||||||
|
cron_jobs:
|
||||||
|
- name: "Deadman health check"
|
||||||
|
job: "cd {{ wizard_home }}/workspace/timmy-config && python3 fleet/health_check.py"
|
||||||
|
minute: "*/5"
|
||||||
|
hour: "*"
|
||||||
|
enabled: "{{ deadman_enabled }}"
|
||||||
|
|
||||||
|
- name: "Muda audit"
|
||||||
|
job: "cd {{ wizard_home }}/workspace/timmy-config && bash fleet/muda-audit.sh >> /tmp/muda-audit.log 2>&1"
|
||||||
|
minute: "0"
|
||||||
|
hour: "21"
|
||||||
|
weekday: "0"
|
||||||
|
enabled: true
|
||||||
|
|
||||||
|
- name: "Config pull from upstream"
|
||||||
|
job: "cd {{ wizard_home }}/workspace/timmy-config && git pull --ff-only origin main"
|
||||||
|
minute: "*/15"
|
||||||
|
hour: "*"
|
||||||
|
enabled: "{{ config_pull_on_wake }}"
|
||||||
|
|
||||||
|
- name: "Request log rotation"
|
||||||
|
job: "python3 -c \"import sqlite3,datetime; db=sqlite3.connect('{{ request_log_path }}'); db.execute('DELETE FROM request_log WHERE timestamp < datetime(\\\"now\\\", \\\"-{{ request_log_rotation_days }} days\\\")'); db.commit()\""
|
||||||
|
minute: "0"
|
||||||
|
hour: "3"
|
||||||
|
enabled: "{{ request_log_enabled }}"
|
||||||
|
|
||||||
|
# --- Provider Enforcement ---
|
||||||
|
# These are validated on every Ansible run. Any Anthropic reference = failure.
|
||||||
|
provider_ban_enforcement: strict # strict = fail playbook, warn = log only
|
||||||
119
ansible/inventory/hosts.yml
Normal file
119
ansible/inventory/hosts.yml
Normal file
@@ -0,0 +1,119 @@
|
|||||||
|
# =============================================================================
|
||||||
|
# Fleet Inventory — The Timmy Foundation
|
||||||
|
# =============================================================================
|
||||||
|
# Source of truth for all machines in the fleet.
|
||||||
|
# Update this file when machines are added/removed.
|
||||||
|
# All changes go through PR review.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
all:
|
||||||
|
children:
|
||||||
|
wizards:
|
||||||
|
hosts:
|
||||||
|
timmy:
|
||||||
|
ansible_host: localhost
|
||||||
|
ansible_connection: local
|
||||||
|
wizard_name: Timmy
|
||||||
|
wizard_role: "Primary wizard — soul of the fleet"
|
||||||
|
wizard_provider_primary: kimi-coding
|
||||||
|
wizard_model_primary: kimi-k2.5
|
||||||
|
hermes_port: 8081
|
||||||
|
api_port: 8645
|
||||||
|
wizard_home: "{{ ansible_env.HOME }}/wizards/timmy"
|
||||||
|
hermes_home: "{{ ansible_env.HOME }}/.hermes"
|
||||||
|
machine_type: mac
|
||||||
|
# Timmy runs on Alexander's M3 Max
|
||||||
|
ollama_available: true
|
||||||
|
|
||||||
|
allegro:
|
||||||
|
ansible_host: 167.99.126.228
|
||||||
|
ansible_user: root
|
||||||
|
wizard_name: Allegro
|
||||||
|
wizard_role: "Kimi-backed third wizard house — tight coding tasks"
|
||||||
|
wizard_provider_primary: kimi-coding
|
||||||
|
wizard_model_primary: kimi-k2.5
|
||||||
|
hermes_port: 8081
|
||||||
|
api_port: 8645
|
||||||
|
wizard_home: /root/wizards/allegro
|
||||||
|
hermes_home: /root/.hermes
|
||||||
|
machine_type: vps
|
||||||
|
ollama_available: false
|
||||||
|
|
||||||
|
bezalel:
|
||||||
|
ansible_host: 159.203.146.185
|
||||||
|
ansible_user: root
|
||||||
|
wizard_name: Bezalel
|
||||||
|
wizard_role: "Forge-and-testbed wizard — infrastructure, deployment, hardening"
|
||||||
|
wizard_provider_primary: kimi-coding
|
||||||
|
wizard_model_primary: kimi-k2.5
|
||||||
|
hermes_port: 8081
|
||||||
|
api_port: 8656
|
||||||
|
wizard_home: /root/wizards/bezalel
|
||||||
|
hermes_home: /root/.hermes
|
||||||
|
machine_type: vps
|
||||||
|
ollama_available: false
|
||||||
|
# NOTE: The awake Bezalel may be the duplicate.
|
||||||
|
# Fleet audit (the-nexus #1144) will resolve identity.
|
||||||
|
|
||||||
|
ezra:
|
||||||
|
ansible_host: 143.198.27.163
|
||||||
|
ansible_user: root
|
||||||
|
wizard_name: Ezra
|
||||||
|
wizard_role: "Infrastructure wizard — Gitea, nginx, hosting"
|
||||||
|
wizard_provider_primary: kimi-coding
|
||||||
|
wizard_model_primary: kimi-k2.5
|
||||||
|
hermes_port: 8081
|
||||||
|
api_port: 8645
|
||||||
|
wizard_home: /root/wizards/ezra
|
||||||
|
hermes_home: /root/.hermes
|
||||||
|
machine_type: vps
|
||||||
|
ollama_available: false
|
||||||
|
# NOTE: Currently DOWN — Telegram key revoked, awaiting propagation.
|
||||||
|
|
||||||
|
# Infrastructure hosts (not wizards, but managed by Ansible)
|
||||||
|
infrastructure:
|
||||||
|
hosts:
|
||||||
|
forge:
|
||||||
|
ansible_host: 143.198.27.163
|
||||||
|
ansible_user: root
|
||||||
|
# Gitea runs on the same box as Ezra
|
||||||
|
gitea_url: https://forge.alexanderwhitestone.com
|
||||||
|
gitea_org: Timmy_Foundation
|
||||||
|
|
||||||
|
vars:
|
||||||
|
# Global variables applied to all hosts
|
||||||
|
gitea_repo_url: "https://forge.alexanderwhitestone.com/Timmy_Foundation/timmy-config.git"
|
||||||
|
gitea_branch: main
|
||||||
|
config_base_path: "{{ gitea_repo_url }}"
|
||||||
|
timmy_log_dir: "~/.local/timmy/fleet-health"
|
||||||
|
request_log_db: "~/.local/timmy/request_log.db"
|
||||||
|
|
||||||
|
# Golden state provider chain — Anthropic is BANNED
|
||||||
|
golden_state_providers:
|
||||||
|
- name: kimi-coding
|
||||||
|
model: kimi-k2.5
|
||||||
|
base_url: "https://api.kimi.com/coding/v1"
|
||||||
|
timeout: 120
|
||||||
|
reason: "Primary — Kimi K2.5 (best value, least friction)"
|
||||||
|
- name: openrouter
|
||||||
|
model: google/gemini-2.5-pro
|
||||||
|
base_url: "https://openrouter.ai/api/v1"
|
||||||
|
api_key_env: OPENROUTER_API_KEY
|
||||||
|
timeout: 120
|
||||||
|
reason: "Fallback — Gemini 2.5 Pro via OpenRouter"
|
||||||
|
- name: ollama
|
||||||
|
model: "gemma4:latest"
|
||||||
|
base_url: "http://localhost:11434/v1"
|
||||||
|
timeout: 180
|
||||||
|
reason: "Terminal fallback — local Ollama (sovereign, no API needed)"
|
||||||
|
|
||||||
|
# Banned providers — hard enforcement
|
||||||
|
banned_providers:
|
||||||
|
- anthropic
|
||||||
|
- claude
|
||||||
|
banned_models_patterns:
|
||||||
|
- "claude-*"
|
||||||
|
- "anthropic/*"
|
||||||
|
- "*sonnet*"
|
||||||
|
- "*opus*"
|
||||||
|
- "*haiku*"
|
||||||
98
ansible/playbooks/agent_startup.yml
Normal file
98
ansible/playbooks/agent_startup.yml
Normal file
@@ -0,0 +1,98 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# agent_startup.yml — Resurrect Wizards from Checked-in Configs
|
||||||
|
# =============================================================================
|
||||||
|
# Brings wizards back online using golden state configs.
|
||||||
|
# Order: pull config → validate → start agent → verify with request_log
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Agent Startup Sequence"
|
||||||
|
hosts: wizards
|
||||||
|
become: true
|
||||||
|
serial: 1 # One wizard at a time to avoid cascading issues
|
||||||
|
|
||||||
|
tasks:
|
||||||
|
- name: "Pull latest config from upstream"
|
||||||
|
git:
|
||||||
|
repo: "{{ upstream_repo }}"
|
||||||
|
dest: "{{ wizard_home }}/workspace/timmy-config"
|
||||||
|
version: "{{ upstream_branch }}"
|
||||||
|
force: true
|
||||||
|
tags: [pull]
|
||||||
|
|
||||||
|
- name: "Deploy golden state config"
|
||||||
|
include_role:
|
||||||
|
name: golden_state
|
||||||
|
tags: [config]
|
||||||
|
|
||||||
|
- name: "Validate config — no banned providers"
|
||||||
|
shell: |
|
||||||
|
python3 -c "
|
||||||
|
import yaml, sys
|
||||||
|
with open('{{ wizard_home }}/config.yaml') as f:
|
||||||
|
cfg = yaml.safe_load(f)
|
||||||
|
banned = {{ banned_providers }}
|
||||||
|
for p in cfg.get('fallback_providers', []):
|
||||||
|
if p.get('provider', '') in banned:
|
||||||
|
print(f'BANNED: {p[\"provider\"]}', file=sys.stderr)
|
||||||
|
sys.exit(1)
|
||||||
|
model = cfg.get('model', {}).get('provider', '')
|
||||||
|
if model in banned:
|
||||||
|
print(f'BANNED default provider: {model}', file=sys.stderr)
|
||||||
|
sys.exit(1)
|
||||||
|
print('Config validated — no banned providers.')
|
||||||
|
"
|
||||||
|
register: config_valid
|
||||||
|
tags: [validate]
|
||||||
|
|
||||||
|
- name: "Ensure hermes-agent service is running"
|
||||||
|
systemd:
|
||||||
|
name: "hermes-{{ wizard_name | lower }}"
|
||||||
|
state: started
|
||||||
|
enabled: true
|
||||||
|
when: machine_type == 'vps'
|
||||||
|
tags: [start]
|
||||||
|
ignore_errors: true # Service may not exist yet on all machines
|
||||||
|
|
||||||
|
- name: "Start hermes agent (Mac — launchctl)"
|
||||||
|
shell: |
|
||||||
|
launchctl kickstart -k "ai.hermes.{{ wizard_name | lower }}" 2>/dev/null || \
|
||||||
|
cd {{ wizard_home }} && hermes agent start --daemon 2>&1 | tail -5
|
||||||
|
when: machine_type == 'mac'
|
||||||
|
tags: [start]
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: "Wait for agent to come online"
|
||||||
|
wait_for:
|
||||||
|
host: 127.0.0.1
|
||||||
|
port: "{{ api_port }}"
|
||||||
|
timeout: 60
|
||||||
|
state: started
|
||||||
|
tags: [verify]
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: "Verify agent is alive — check request_log for activity"
|
||||||
|
shell: |
|
||||||
|
sleep 10
|
||||||
|
python3 -c "
|
||||||
|
import sqlite3, sys
|
||||||
|
db = sqlite3.connect('{{ request_log_path }}')
|
||||||
|
cursor = db.execute('''
|
||||||
|
SELECT COUNT(*) FROM request_log
|
||||||
|
WHERE agent_name = '{{ wizard_name }}'
|
||||||
|
AND timestamp > datetime('now', '-5 minutes')
|
||||||
|
''')
|
||||||
|
count = cursor.fetchone()[0]
|
||||||
|
if count > 0:
|
||||||
|
print(f'{{ wizard_name }} is alive — {count} recent inference calls logged.')
|
||||||
|
else:
|
||||||
|
print(f'WARNING: {{ wizard_name }} started but no telemetry yet.')
|
||||||
|
"
|
||||||
|
register: agent_status
|
||||||
|
tags: [verify]
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: "Report startup status"
|
||||||
|
debug:
|
||||||
|
msg: "{{ wizard_name }}: {{ agent_status.stdout | default('startup attempted') }}"
|
||||||
|
tags: [always]
|
||||||
15
ansible/playbooks/cron_schedule.yml
Normal file
15
ansible/playbooks/cron_schedule.yml
Normal file
@@ -0,0 +1,15 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# cron_schedule.yml — Source-Controlled Cron Jobs
|
||||||
|
# =============================================================================
|
||||||
|
# All cron jobs are defined in group_vars/wizards.yml.
|
||||||
|
# This playbook deploys them. No manual crontab edits allowed.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Deploy Cron Schedule"
|
||||||
|
hosts: wizards
|
||||||
|
become: true
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: cron_manager
|
||||||
|
tags: [cron, schedule]
|
||||||
17
ansible/playbooks/deadman_switch.yml
Normal file
17
ansible/playbooks/deadman_switch.yml
Normal file
@@ -0,0 +1,17 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# deadman_switch.yml — Deploy Deadman Switch to All Wizards
|
||||||
|
# =============================================================================
|
||||||
|
# The deadman watch already fires and detects dead agents.
|
||||||
|
# This playbook wires the ACTION:
|
||||||
|
# - On healthy check: snapshot current config as "last known good"
|
||||||
|
# - On failed check: rollback config to snapshot, restart agent
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Deploy Deadman Switch ACTION"
|
||||||
|
hosts: wizards
|
||||||
|
become: true
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: deadman_switch
|
||||||
|
tags: [deadman, recovery]
|
||||||
30
ansible/playbooks/golden_state.yml
Normal file
30
ansible/playbooks/golden_state.yml
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# golden_state.yml — Deploy Golden State Config to All Wizards
|
||||||
|
# =============================================================================
|
||||||
|
# Enforces the golden state provider chain across the fleet.
|
||||||
|
# Removes any Anthropic references. Deploys the approved provider chain.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Deploy Golden State Configuration"
|
||||||
|
hosts: wizards
|
||||||
|
become: true
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: golden_state
|
||||||
|
tags: [golden, config]
|
||||||
|
|
||||||
|
post_tasks:
|
||||||
|
- name: "Verify golden state — no banned providers"
|
||||||
|
shell: |
|
||||||
|
grep -rci 'anthropic\|claude-sonnet\|claude-opus\|claude-haiku' \
|
||||||
|
{{ hermes_home }}/config.yaml \
|
||||||
|
{{ wizard_home }}/config.yaml 2>/dev/null || echo "0"
|
||||||
|
register: banned_count
|
||||||
|
changed_when: false
|
||||||
|
|
||||||
|
- name: "Report golden state status"
|
||||||
|
debug:
|
||||||
|
msg: >
|
||||||
|
{{ wizard_name }} golden state: {{ golden_state_providers | map(attribute='name') | list | join(' → ') }}.
|
||||||
|
Banned provider references: {{ banned_count.stdout | trim }}.
|
||||||
15
ansible/playbooks/request_log.yml
Normal file
15
ansible/playbooks/request_log.yml
Normal file
@@ -0,0 +1,15 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# request_log.yml — Deploy Telemetry Table
|
||||||
|
# =============================================================================
|
||||||
|
# Creates the request_log SQLite table on all machines.
|
||||||
|
# Every inference call writes a row. No exceptions. No summarizing.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Deploy Request Log Telemetry"
|
||||||
|
hosts: wizards
|
||||||
|
become: true
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: request_log
|
||||||
|
tags: [telemetry, logging]
|
||||||
72
ansible/playbooks/site.yml
Normal file
72
ansible/playbooks/site.yml
Normal file
@@ -0,0 +1,72 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# site.yml — Master Playbook for the Timmy Foundation Fleet
|
||||||
|
# =============================================================================
|
||||||
|
# This is the ONE playbook that defines the entire fleet state.
|
||||||
|
# Run this and every machine converges to golden state.
|
||||||
|
#
|
||||||
|
# Usage:
|
||||||
|
# ansible-playbook -i inventory/hosts.yml playbooks/site.yml
|
||||||
|
# ansible-playbook -i inventory/hosts.yml playbooks/site.yml --limit bezalel
|
||||||
|
# ansible-playbook -i inventory/hosts.yml playbooks/site.yml --check --diff
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Timmy Foundation Fleet — Full Convergence"
|
||||||
|
hosts: wizards
|
||||||
|
become: true
|
||||||
|
|
||||||
|
pre_tasks:
|
||||||
|
- name: "Validate no banned providers in golden state"
|
||||||
|
assert:
|
||||||
|
that:
|
||||||
|
- "item.name not in banned_providers"
|
||||||
|
fail_msg: "BANNED PROVIDER DETECTED: {{ item.name }} — Anthropic is permanently banned."
|
||||||
|
quiet: true
|
||||||
|
loop: "{{ golden_state_providers }}"
|
||||||
|
tags: [always]
|
||||||
|
|
||||||
|
- name: "Display target wizard"
|
||||||
|
debug:
|
||||||
|
msg: "Deploying to {{ wizard_name }} ({{ wizard_role }}) on {{ ansible_host }}"
|
||||||
|
tags: [always]
|
||||||
|
|
||||||
|
roles:
|
||||||
|
- role: wizard_base
|
||||||
|
tags: [base, setup]
|
||||||
|
|
||||||
|
- role: golden_state
|
||||||
|
tags: [golden, config]
|
||||||
|
|
||||||
|
- role: deadman_switch
|
||||||
|
tags: [deadman, recovery]
|
||||||
|
|
||||||
|
- role: request_log
|
||||||
|
tags: [telemetry, logging]
|
||||||
|
|
||||||
|
- role: cron_manager
|
||||||
|
tags: [cron, schedule]
|
||||||
|
|
||||||
|
post_tasks:
|
||||||
|
- name: "Final validation — scan for banned providers"
|
||||||
|
shell: |
|
||||||
|
grep -ri 'anthropic\|claude-sonnet\|claude-opus\|claude-haiku' \
|
||||||
|
{{ hermes_home }}/config.yaml \
|
||||||
|
{{ wizard_home }}/config.yaml \
|
||||||
|
{{ thin_config_path }} 2>/dev/null || true
|
||||||
|
register: banned_scan
|
||||||
|
changed_when: false
|
||||||
|
tags: [validation]
|
||||||
|
|
||||||
|
- name: "FAIL if banned providers found in deployed config"
|
||||||
|
fail:
|
||||||
|
msg: |
|
||||||
|
BANNED PROVIDER DETECTED IN DEPLOYED CONFIG:
|
||||||
|
{{ banned_scan.stdout }}
|
||||||
|
Anthropic is permanently banned. Fix the config and re-deploy.
|
||||||
|
when: banned_scan.stdout | length > 0
|
||||||
|
tags: [validation]
|
||||||
|
|
||||||
|
- name: "Deployment complete"
|
||||||
|
debug:
|
||||||
|
msg: "{{ wizard_name }} converged to golden state. Provider chain: {{ golden_state_providers | map(attribute='name') | list | join(' → ') }}"
|
||||||
|
tags: [always]
|
||||||
55
ansible/roles/cron_manager/tasks/main.yml
Normal file
55
ansible/roles/cron_manager/tasks/main.yml
Normal file
@@ -0,0 +1,55 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# cron_manager/tasks — Source-Controlled Cron Jobs
|
||||||
|
# =============================================================================
|
||||||
|
# All cron jobs are defined in group_vars/wizards.yml.
|
||||||
|
# No manual crontab edits. This is the only way to manage cron.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Deploy managed cron jobs"
|
||||||
|
cron:
|
||||||
|
name: "{{ item.name }}"
|
||||||
|
job: "{{ item.job }}"
|
||||||
|
minute: "{{ item.minute | default('*') }}"
|
||||||
|
hour: "{{ item.hour | default('*') }}"
|
||||||
|
day: "{{ item.day | default('*') }}"
|
||||||
|
month: "{{ item.month | default('*') }}"
|
||||||
|
weekday: "{{ item.weekday | default('*') }}"
|
||||||
|
state: "{{ 'present' if item.enabled else 'absent' }}"
|
||||||
|
user: "{{ ansible_user | default('root') }}"
|
||||||
|
loop: "{{ cron_jobs }}"
|
||||||
|
when: cron_jobs is defined
|
||||||
|
|
||||||
|
- name: "Deploy deadman switch cron (fallback if systemd timer unavailable)"
|
||||||
|
cron:
|
||||||
|
name: "Deadman switch — {{ wizard_name }}"
|
||||||
|
job: "{{ wizard_home }}/deadman_action.sh >> {{ timmy_log_dir }}/deadman-{{ wizard_name }}.log 2>&1"
|
||||||
|
minute: "*/5"
|
||||||
|
hour: "*"
|
||||||
|
state: present
|
||||||
|
user: "{{ ansible_user | default('root') }}"
|
||||||
|
when: deadman_enabled and machine_type != 'vps'
|
||||||
|
# VPS machines use systemd timers instead
|
||||||
|
|
||||||
|
- name: "Remove legacy cron jobs (cleanup)"
|
||||||
|
cron:
|
||||||
|
name: "{{ item }}"
|
||||||
|
state: absent
|
||||||
|
user: "{{ ansible_user | default('root') }}"
|
||||||
|
loop:
|
||||||
|
- "legacy-deadman-watch"
|
||||||
|
- "old-health-check"
|
||||||
|
- "backup-deadman"
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: "List active cron jobs"
|
||||||
|
shell: "crontab -l 2>/dev/null | grep -v '^#' | grep -v '^$' || echo 'No cron jobs found.'"
|
||||||
|
register: active_crons
|
||||||
|
changed_when: false
|
||||||
|
|
||||||
|
- name: "Report cron status"
|
||||||
|
debug:
|
||||||
|
msg: |
|
||||||
|
{{ wizard_name }} cron jobs deployed.
|
||||||
|
Active:
|
||||||
|
{{ active_crons.stdout }}
|
||||||
17
ansible/roles/deadman_switch/handlers/main.yml
Normal file
17
ansible/roles/deadman_switch/handlers/main.yml
Normal file
@@ -0,0 +1,17 @@
|
|||||||
|
---
|
||||||
|
- name: "Enable deadman service"
|
||||||
|
systemd:
|
||||||
|
name: "deadman-{{ wizard_name | lower }}.service"
|
||||||
|
daemon_reload: true
|
||||||
|
enabled: true
|
||||||
|
|
||||||
|
- name: "Enable deadman timer"
|
||||||
|
systemd:
|
||||||
|
name: "deadman-{{ wizard_name | lower }}.timer"
|
||||||
|
daemon_reload: true
|
||||||
|
enabled: true
|
||||||
|
state: started
|
||||||
|
|
||||||
|
- name: "Load deadman plist"
|
||||||
|
shell: "launchctl load {{ ansible_env.HOME }}/Library/LaunchAgents/com.timmy.deadman.{{ wizard_name | lower }}.plist"
|
||||||
|
ignore_errors: true
|
||||||
53
ansible/roles/deadman_switch/tasks/main.yml
Normal file
53
ansible/roles/deadman_switch/tasks/main.yml
Normal file
@@ -0,0 +1,53 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# deadman_switch/tasks — Wire the Deadman Switch ACTION
|
||||||
|
# =============================================================================
|
||||||
|
# The watch fires. This makes it DO something:
|
||||||
|
# - On healthy check: snapshot current config as "last known good"
|
||||||
|
# - On failed check: rollback to last known good, restart agent
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Create snapshot directory"
|
||||||
|
file:
|
||||||
|
path: "{{ deadman_snapshot_dir }}"
|
||||||
|
state: directory
|
||||||
|
mode: "0755"
|
||||||
|
|
||||||
|
- name: "Deploy deadman switch script"
|
||||||
|
template:
|
||||||
|
src: deadman_action.sh.j2
|
||||||
|
dest: "{{ wizard_home }}/deadman_action.sh"
|
||||||
|
mode: "0755"
|
||||||
|
|
||||||
|
- name: "Deploy deadman systemd service"
|
||||||
|
template:
|
||||||
|
src: deadman_switch.service.j2
|
||||||
|
dest: "/etc/systemd/system/deadman-{{ wizard_name | lower }}.service"
|
||||||
|
mode: "0644"
|
||||||
|
when: machine_type == 'vps'
|
||||||
|
notify: "Enable deadman service"
|
||||||
|
|
||||||
|
- name: "Deploy deadman systemd timer"
|
||||||
|
template:
|
||||||
|
src: deadman_switch.timer.j2
|
||||||
|
dest: "/etc/systemd/system/deadman-{{ wizard_name | lower }}.timer"
|
||||||
|
mode: "0644"
|
||||||
|
when: machine_type == 'vps'
|
||||||
|
notify: "Enable deadman timer"
|
||||||
|
|
||||||
|
- name: "Deploy deadman launchd plist (Mac)"
|
||||||
|
template:
|
||||||
|
src: deadman_switch.plist.j2
|
||||||
|
dest: "{{ ansible_env.HOME }}/Library/LaunchAgents/com.timmy.deadman.{{ wizard_name | lower }}.plist"
|
||||||
|
mode: "0644"
|
||||||
|
when: machine_type == 'mac'
|
||||||
|
notify: "Load deadman plist"
|
||||||
|
|
||||||
|
- name: "Take initial config snapshot"
|
||||||
|
copy:
|
||||||
|
src: "{{ wizard_home }}/config.yaml"
|
||||||
|
dest: "{{ deadman_snapshot_dir }}/config.yaml.known_good"
|
||||||
|
remote_src: true
|
||||||
|
mode: "0444"
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
153
ansible/roles/deadman_switch/templates/deadman_action.sh.j2
Normal file
153
ansible/roles/deadman_switch/templates/deadman_action.sh.j2
Normal file
@@ -0,0 +1,153 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# =============================================================================
|
||||||
|
# Deadman Switch ACTION — {{ wizard_name }}
|
||||||
|
# =============================================================================
|
||||||
|
# Generated by Ansible on {{ ansible_date_time.iso8601 }}
|
||||||
|
# DO NOT EDIT MANUALLY.
|
||||||
|
#
|
||||||
|
# On healthy check: snapshot current config as "last known good"
|
||||||
|
# On failed check: rollback config to last known good, restart agent
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
WIZARD_NAME="{{ wizard_name }}"
|
||||||
|
WIZARD_HOME="{{ wizard_home }}"
|
||||||
|
CONFIG_FILE="{{ wizard_home }}/config.yaml"
|
||||||
|
SNAPSHOT_DIR="{{ deadman_snapshot_dir }}"
|
||||||
|
SNAPSHOT_FILE="${SNAPSHOT_DIR}/config.yaml.known_good"
|
||||||
|
REQUEST_LOG_DB="{{ request_log_path }}"
|
||||||
|
LOG_DIR="{{ timmy_log_dir }}"
|
||||||
|
LOG_FILE="${LOG_DIR}/deadman-${WIZARD_NAME}.log"
|
||||||
|
MAX_SNAPSHOTS={{ deadman_max_snapshots }}
|
||||||
|
RESTART_COOLDOWN={{ deadman_restart_cooldown }}
|
||||||
|
MAX_RESTART_ATTEMPTS={{ deadman_max_restart_attempts }}
|
||||||
|
COOLDOWN_FILE="${LOG_DIR}/deadman_cooldown_${WIZARD_NAME}"
|
||||||
|
SERVICE_NAME="hermes-{{ wizard_name | lower }}"
|
||||||
|
|
||||||
|
# Ensure directories exist
|
||||||
|
mkdir -p "${SNAPSHOT_DIR}" "${LOG_DIR}"
|
||||||
|
|
||||||
|
log() {
|
||||||
|
echo "[$(date -u +%Y-%m-%dT%H:%M:%SZ)] [deadman] [${WIZARD_NAME}] $*" >> "${LOG_FILE}"
|
||||||
|
echo "[deadman] [${WIZARD_NAME}] $*"
|
||||||
|
}
|
||||||
|
|
||||||
|
log_telemetry() {
|
||||||
|
local status="$1"
|
||||||
|
local message="$2"
|
||||||
|
if [ -f "${REQUEST_LOG_DB}" ]; then
|
||||||
|
sqlite3 "${REQUEST_LOG_DB}" "INSERT INTO request_log (timestamp, agent_name, provider, model, endpoint, status, error_message) VALUES (datetime('now'), '${WIZARD_NAME}', 'deadman_switch', 'N/A', 'health_check', '${status}', '${message}');" 2>/dev/null || true
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
snapshot_config() {
|
||||||
|
if [ -f "${CONFIG_FILE}" ]; then
|
||||||
|
cp "${CONFIG_FILE}" "${SNAPSHOT_FILE}"
|
||||||
|
# Keep rolling history
|
||||||
|
cp "${CONFIG_FILE}" "${SNAPSHOT_DIR}/config.yaml.$(date +%s)"
|
||||||
|
# Prune old snapshots
|
||||||
|
ls -t "${SNAPSHOT_DIR}"/config.yaml.[0-9]* 2>/dev/null | tail -n +$((MAX_SNAPSHOTS + 1)) | xargs rm -f 2>/dev/null
|
||||||
|
log "Config snapshot saved."
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
rollback_config() {
|
||||||
|
if [ -f "${SNAPSHOT_FILE}" ]; then
|
||||||
|
log "Rolling back config to last known good..."
|
||||||
|
cp "${SNAPSHOT_FILE}" "${CONFIG_FILE}"
|
||||||
|
log "Config rolled back."
|
||||||
|
log_telemetry "fallback" "Config rolled back to last known good by deadman switch"
|
||||||
|
else
|
||||||
|
log "ERROR: No known good snapshot found. Pulling from upstream..."
|
||||||
|
cd "${WIZARD_HOME}/workspace/timmy-config" 2>/dev/null && \
|
||||||
|
git pull --ff-only origin {{ upstream_branch }} 2>/dev/null && \
|
||||||
|
cp "wizards/{{ wizard_name | lower }}/config.yaml" "${CONFIG_FILE}" && \
|
||||||
|
log "Config restored from upstream." || \
|
||||||
|
log "CRITICAL: Cannot restore config from any source."
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
restart_agent() {
|
||||||
|
# Check cooldown
|
||||||
|
if [ -f "${COOLDOWN_FILE}" ]; then
|
||||||
|
local last_restart
|
||||||
|
last_restart=$(cat "${COOLDOWN_FILE}")
|
||||||
|
local now
|
||||||
|
now=$(date +%s)
|
||||||
|
local elapsed=$((now - last_restart))
|
||||||
|
if [ "${elapsed}" -lt "${RESTART_COOLDOWN}" ]; then
|
||||||
|
log "Restart cooldown active (${elapsed}s / ${RESTART_COOLDOWN}s). Skipping."
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
|
log "Restarting ${SERVICE_NAME}..."
|
||||||
|
date +%s > "${COOLDOWN_FILE}"
|
||||||
|
|
||||||
|
{% if machine_type == 'vps' %}
|
||||||
|
systemctl restart "${SERVICE_NAME}" 2>/dev/null && \
|
||||||
|
log "Agent restarted via systemd." || \
|
||||||
|
log "ERROR: systemd restart failed."
|
||||||
|
{% else %}
|
||||||
|
launchctl kickstart -k "ai.hermes.{{ wizard_name | lower }}" 2>/dev/null && \
|
||||||
|
log "Agent restarted via launchctl." || \
|
||||||
|
(cd "${WIZARD_HOME}" && hermes agent start --daemon 2>/dev/null && \
|
||||||
|
log "Agent restarted via hermes CLI.") || \
|
||||||
|
log "ERROR: All restart methods failed."
|
||||||
|
{% endif %}
|
||||||
|
|
||||||
|
log_telemetry "success" "Agent restarted by deadman switch"
|
||||||
|
}
|
||||||
|
|
||||||
|
# --- Health Check ---
|
||||||
|
check_health() {
|
||||||
|
# Check 1: Is the agent process running?
|
||||||
|
{% if machine_type == 'vps' %}
|
||||||
|
if ! systemctl is-active --quiet "${SERVICE_NAME}" 2>/dev/null; then
|
||||||
|
if ! pgrep -f "hermes" > /dev/null 2>/dev/null; then
|
||||||
|
log "FAIL: Agent process not running."
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
{% else %}
|
||||||
|
if ! pgrep -f "hermes" > /dev/null 2>/dev/null; then
|
||||||
|
log "FAIL: Agent process not running."
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
{% endif %}
|
||||||
|
|
||||||
|
# Check 2: Is the API port responding?
|
||||||
|
if ! timeout 10 bash -c "echo > /dev/tcp/127.0.0.1/{{ api_port }}" 2>/dev/null; then
|
||||||
|
log "FAIL: API port {{ api_port }} not responding."
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
# Check 3: Does the config contain banned providers?
|
||||||
|
if grep -qi 'anthropic\|claude-sonnet\|claude-opus\|claude-haiku' "${CONFIG_FILE}" 2>/dev/null; then
|
||||||
|
log "FAIL: Config contains banned provider (Anthropic). Rolling back."
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
return 0
|
||||||
|
}
|
||||||
|
|
||||||
|
# --- Main ---
|
||||||
|
main() {
|
||||||
|
log "Health check starting..."
|
||||||
|
|
||||||
|
if check_health; then
|
||||||
|
log "HEALTHY — snapshotting config."
|
||||||
|
snapshot_config
|
||||||
|
log_telemetry "success" "Health check passed"
|
||||||
|
else
|
||||||
|
log "UNHEALTHY — initiating recovery."
|
||||||
|
log_telemetry "error" "Health check failed — initiating rollback"
|
||||||
|
rollback_config
|
||||||
|
restart_agent
|
||||||
|
fi
|
||||||
|
|
||||||
|
log "Health check complete."
|
||||||
|
}
|
||||||
|
|
||||||
|
main "$@"
|
||||||
@@ -0,0 +1,22 @@
|
|||||||
|
<?xml version="1.0" encoding="UTF-8"?>
|
||||||
|
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
|
||||||
|
<!-- Deadman Switch — {{ wizard_name }}. Generated by Ansible. DO NOT EDIT MANUALLY. -->
|
||||||
|
<plist version="1.0">
|
||||||
|
<dict>
|
||||||
|
<key>Label</key>
|
||||||
|
<string>com.timmy.deadman.{{ wizard_name | lower }}</string>
|
||||||
|
<key>ProgramArguments</key>
|
||||||
|
<array>
|
||||||
|
<string>/bin/bash</string>
|
||||||
|
<string>{{ wizard_home }}/deadman_action.sh</string>
|
||||||
|
</array>
|
||||||
|
<key>StartInterval</key>
|
||||||
|
<integer>{{ deadman_check_interval }}</integer>
|
||||||
|
<key>RunAtLoad</key>
|
||||||
|
<true/>
|
||||||
|
<key>StandardOutPath</key>
|
||||||
|
<string>{{ timmy_log_dir }}/deadman-{{ wizard_name }}.log</string>
|
||||||
|
<key>StandardErrorPath</key>
|
||||||
|
<string>{{ timmy_log_dir }}/deadman-{{ wizard_name }}.log</string>
|
||||||
|
</dict>
|
||||||
|
</plist>
|
||||||
@@ -0,0 +1,16 @@
|
|||||||
|
# Deadman Switch — {{ wizard_name }}
|
||||||
|
# Generated by Ansible. DO NOT EDIT MANUALLY.
|
||||||
|
|
||||||
|
[Unit]
|
||||||
|
Description=Deadman Switch for {{ wizard_name }} wizard
|
||||||
|
After=network.target
|
||||||
|
|
||||||
|
[Service]
|
||||||
|
Type=oneshot
|
||||||
|
ExecStart={{ wizard_home }}/deadman_action.sh
|
||||||
|
User={{ ansible_user | default('root') }}
|
||||||
|
StandardOutput=append:{{ timmy_log_dir }}/deadman-{{ wizard_name }}.log
|
||||||
|
StandardError=append:{{ timmy_log_dir }}/deadman-{{ wizard_name }}.log
|
||||||
|
|
||||||
|
[Install]
|
||||||
|
WantedBy=multi-user.target
|
||||||
@@ -0,0 +1,14 @@
|
|||||||
|
# Deadman Switch Timer — {{ wizard_name }}
|
||||||
|
# Generated by Ansible. DO NOT EDIT MANUALLY.
|
||||||
|
# Runs every {{ deadman_check_interval // 60 }} minutes.
|
||||||
|
|
||||||
|
[Unit]
|
||||||
|
Description=Deadman Switch Timer for {{ wizard_name }} wizard
|
||||||
|
|
||||||
|
[Timer]
|
||||||
|
OnBootSec=60
|
||||||
|
OnUnitActiveSec={{ deadman_check_interval }}s
|
||||||
|
AccuracySec=30s
|
||||||
|
|
||||||
|
[Install]
|
||||||
|
WantedBy=timers.target
|
||||||
6
ansible/roles/golden_state/defaults/main.yml
Normal file
6
ansible/roles/golden_state/defaults/main.yml
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
---
|
||||||
|
# golden_state defaults
|
||||||
|
# The golden_state_providers list is defined in group_vars/wizards.yml
|
||||||
|
# and inventory/hosts.yml (global vars).
|
||||||
|
golden_state_enforce: true
|
||||||
|
golden_state_backup_before_deploy: true
|
||||||
46
ansible/roles/golden_state/tasks/main.yml
Normal file
46
ansible/roles/golden_state/tasks/main.yml
Normal file
@@ -0,0 +1,46 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# golden_state/tasks — Deploy and enforce golden state provider chain
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Backup current config before golden state deploy"
|
||||||
|
copy:
|
||||||
|
src: "{{ wizard_home }}/config.yaml"
|
||||||
|
dest: "{{ wizard_home }}/config.yaml.pre-golden-{{ ansible_date_time.epoch }}"
|
||||||
|
remote_src: true
|
||||||
|
when: golden_state_backup_before_deploy
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: "Deploy golden state wizard config"
|
||||||
|
template:
|
||||||
|
src: "../../wizard_base/templates/wizard_config.yaml.j2"
|
||||||
|
dest: "{{ wizard_home }}/config.yaml"
|
||||||
|
mode: "0644"
|
||||||
|
backup: true
|
||||||
|
notify:
|
||||||
|
- "Restart hermes agent (systemd)"
|
||||||
|
- "Restart hermes agent (launchctl)"
|
||||||
|
|
||||||
|
- name: "Scan for banned providers in all config files"
|
||||||
|
shell: |
|
||||||
|
FOUND=0
|
||||||
|
for f in {{ wizard_home }}/config.yaml {{ hermes_home }}/config.yaml; do
|
||||||
|
if [ -f "$f" ]; then
|
||||||
|
if grep -qi 'anthropic\|claude-sonnet\|claude-opus\|claude-haiku' "$f"; then
|
||||||
|
echo "BANNED PROVIDER in $f:"
|
||||||
|
grep -ni 'anthropic\|claude-sonnet\|claude-opus\|claude-haiku' "$f"
|
||||||
|
FOUND=1
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
done
|
||||||
|
exit $FOUND
|
||||||
|
register: provider_scan
|
||||||
|
changed_when: false
|
||||||
|
failed_when: provider_scan.rc != 0 and provider_ban_enforcement == 'strict'
|
||||||
|
|
||||||
|
- name: "Report golden state deployment"
|
||||||
|
debug:
|
||||||
|
msg: >
|
||||||
|
{{ wizard_name }} golden state deployed.
|
||||||
|
Provider chain: {{ golden_state_providers | map(attribute='name') | list | join(' → ') }}.
|
||||||
|
Banned provider scan: {{ 'CLEAN' if provider_scan.rc == 0 else 'VIOLATIONS FOUND' }}.
|
||||||
64
ansible/roles/request_log/files/request_log_schema.sql
Normal file
64
ansible/roles/request_log/files/request_log_schema.sql
Normal file
@@ -0,0 +1,64 @@
|
|||||||
|
-- =============================================================================
|
||||||
|
-- request_log — Inference Telemetry Table
|
||||||
|
-- =============================================================================
|
||||||
|
-- Every agent writes to this table BEFORE and AFTER every inference call.
|
||||||
|
-- No exceptions. No summarizing. No describing what you would log.
|
||||||
|
-- Actually write the row.
|
||||||
|
--
|
||||||
|
-- Source: KT Bezalel Architecture Session 2026-04-08
|
||||||
|
-- =============================================================================
|
||||||
|
|
||||||
|
CREATE TABLE IF NOT EXISTS request_log (
|
||||||
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||||
|
timestamp TEXT NOT NULL DEFAULT (datetime('now')),
|
||||||
|
agent_name TEXT NOT NULL,
|
||||||
|
provider TEXT NOT NULL,
|
||||||
|
model TEXT NOT NULL,
|
||||||
|
endpoint TEXT NOT NULL,
|
||||||
|
tokens_in INTEGER,
|
||||||
|
tokens_out INTEGER,
|
||||||
|
latency_ms INTEGER,
|
||||||
|
status TEXT NOT NULL, -- 'success', 'error', 'timeout', 'fallback'
|
||||||
|
error_message TEXT
|
||||||
|
);
|
||||||
|
|
||||||
|
-- Index for common queries
|
||||||
|
CREATE INDEX IF NOT EXISTS idx_request_log_agent
|
||||||
|
ON request_log (agent_name, timestamp);
|
||||||
|
|
||||||
|
CREATE INDEX IF NOT EXISTS idx_request_log_provider
|
||||||
|
ON request_log (provider, timestamp);
|
||||||
|
|
||||||
|
CREATE INDEX IF NOT EXISTS idx_request_log_status
|
||||||
|
ON request_log (status, timestamp);
|
||||||
|
|
||||||
|
-- View: recent activity per agent (last hour)
|
||||||
|
CREATE VIEW IF NOT EXISTS v_recent_activity AS
|
||||||
|
SELECT
|
||||||
|
agent_name,
|
||||||
|
provider,
|
||||||
|
model,
|
||||||
|
status,
|
||||||
|
COUNT(*) as call_count,
|
||||||
|
AVG(latency_ms) as avg_latency_ms,
|
||||||
|
SUM(tokens_in) as total_tokens_in,
|
||||||
|
SUM(tokens_out) as total_tokens_out
|
||||||
|
FROM request_log
|
||||||
|
WHERE timestamp > datetime('now', '-1 hour')
|
||||||
|
GROUP BY agent_name, provider, model, status;
|
||||||
|
|
||||||
|
-- View: provider reliability (last 24 hours)
|
||||||
|
CREATE VIEW IF NOT EXISTS v_provider_reliability AS
|
||||||
|
SELECT
|
||||||
|
provider,
|
||||||
|
model,
|
||||||
|
COUNT(*) as total_calls,
|
||||||
|
SUM(CASE WHEN status = 'success' THEN 1 ELSE 0 END) as successes,
|
||||||
|
SUM(CASE WHEN status = 'error' THEN 1 ELSE 0 END) as errors,
|
||||||
|
SUM(CASE WHEN status = 'timeout' THEN 1 ELSE 0 END) as timeouts,
|
||||||
|
SUM(CASE WHEN status = 'fallback' THEN 1 ELSE 0 END) as fallbacks,
|
||||||
|
ROUND(100.0 * SUM(CASE WHEN status = 'success' THEN 1 ELSE 0 END) / COUNT(*), 1) as success_rate,
|
||||||
|
AVG(latency_ms) as avg_latency_ms
|
||||||
|
FROM request_log
|
||||||
|
WHERE timestamp > datetime('now', '-24 hours')
|
||||||
|
GROUP BY provider, model;
|
||||||
50
ansible/roles/request_log/tasks/main.yml
Normal file
50
ansible/roles/request_log/tasks/main.yml
Normal file
@@ -0,0 +1,50 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# request_log/tasks — Deploy Telemetry Table
|
||||||
|
# =============================================================================
|
||||||
|
# "This is non-negotiable infrastructure. Without it, we cannot verify
|
||||||
|
# if any agent actually executed what it claims."
|
||||||
|
# — KT Bezalel 2026-04-08
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Create telemetry directory"
|
||||||
|
file:
|
||||||
|
path: "{{ request_log_path | dirname }}"
|
||||||
|
state: directory
|
||||||
|
mode: "0755"
|
||||||
|
|
||||||
|
- name: "Deploy request_log schema"
|
||||||
|
copy:
|
||||||
|
src: request_log_schema.sql
|
||||||
|
dest: "{{ wizard_home }}/request_log_schema.sql"
|
||||||
|
mode: "0644"
|
||||||
|
|
||||||
|
- name: "Initialize request_log database"
|
||||||
|
shell: |
|
||||||
|
sqlite3 "{{ request_log_path }}" < "{{ wizard_home }}/request_log_schema.sql"
|
||||||
|
args:
|
||||||
|
creates: "{{ request_log_path }}"
|
||||||
|
|
||||||
|
- name: "Verify request_log table exists"
|
||||||
|
shell: |
|
||||||
|
sqlite3 "{{ request_log_path }}" ".tables" | grep -q "request_log"
|
||||||
|
register: table_check
|
||||||
|
changed_when: false
|
||||||
|
|
||||||
|
- name: "Verify request_log schema matches"
|
||||||
|
shell: |
|
||||||
|
sqlite3 "{{ request_log_path }}" ".schema request_log" | grep -q "agent_name"
|
||||||
|
register: schema_check
|
||||||
|
changed_when: false
|
||||||
|
|
||||||
|
- name: "Set permissions on request_log database"
|
||||||
|
file:
|
||||||
|
path: "{{ request_log_path }}"
|
||||||
|
mode: "0644"
|
||||||
|
|
||||||
|
- name: "Report request_log status"
|
||||||
|
debug:
|
||||||
|
msg: >
|
||||||
|
{{ wizard_name }} request_log: {{ request_log_path }}
|
||||||
|
— table exists: {{ table_check.rc == 0 }}
|
||||||
|
— schema valid: {{ schema_check.rc == 0 }}
|
||||||
6
ansible/roles/wizard_base/defaults/main.yml
Normal file
6
ansible/roles/wizard_base/defaults/main.yml
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
---
|
||||||
|
# wizard_base defaults
|
||||||
|
wizard_user: "{{ ansible_user | default('root') }}"
|
||||||
|
wizard_group: "{{ ansible_user | default('root') }}"
|
||||||
|
timmy_base_dir: "~/.local/timmy"
|
||||||
|
timmy_config_repo: "https://forge.alexanderwhitestone.com/Timmy_Foundation/timmy-config.git"
|
||||||
11
ansible/roles/wizard_base/handlers/main.yml
Normal file
11
ansible/roles/wizard_base/handlers/main.yml
Normal file
@@ -0,0 +1,11 @@
|
|||||||
|
---
|
||||||
|
- name: "Restart hermes agent (systemd)"
|
||||||
|
systemd:
|
||||||
|
name: "hermes-{{ wizard_name | lower }}"
|
||||||
|
state: restarted
|
||||||
|
when: machine_type == 'vps'
|
||||||
|
|
||||||
|
- name: "Restart hermes agent (launchctl)"
|
||||||
|
shell: "launchctl kickstart -k ai.hermes.{{ wizard_name | lower }}"
|
||||||
|
when: machine_type == 'mac'
|
||||||
|
ignore_errors: true
|
||||||
69
ansible/roles/wizard_base/tasks/main.yml
Normal file
69
ansible/roles/wizard_base/tasks/main.yml
Normal file
@@ -0,0 +1,69 @@
|
|||||||
|
---
|
||||||
|
# =============================================================================
|
||||||
|
# wizard_base/tasks — Common wizard setup
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
- name: "Create wizard directories"
|
||||||
|
file:
|
||||||
|
path: "{{ item }}"
|
||||||
|
state: directory
|
||||||
|
mode: "0755"
|
||||||
|
loop:
|
||||||
|
- "{{ wizard_home }}"
|
||||||
|
- "{{ wizard_home }}/workspace"
|
||||||
|
- "{{ hermes_home }}"
|
||||||
|
- "{{ hermes_home }}/bin"
|
||||||
|
- "{{ hermes_home }}/skins"
|
||||||
|
- "{{ hermes_home }}/playbooks"
|
||||||
|
- "{{ hermes_home }}/memories"
|
||||||
|
- "~/.local/timmy"
|
||||||
|
- "~/.local/timmy/fleet-health"
|
||||||
|
- "~/.local/timmy/snapshots"
|
||||||
|
- "~/.timmy"
|
||||||
|
|
||||||
|
- name: "Clone/update timmy-config"
|
||||||
|
git:
|
||||||
|
repo: "{{ upstream_repo }}"
|
||||||
|
dest: "{{ wizard_home }}/workspace/timmy-config"
|
||||||
|
version: "{{ upstream_branch }}"
|
||||||
|
force: false
|
||||||
|
update: true
|
||||||
|
ignore_errors: true # May fail on first run if no SSH key
|
||||||
|
|
||||||
|
- name: "Deploy SOUL.md"
|
||||||
|
copy:
|
||||||
|
src: "{{ wizard_home }}/workspace/timmy-config/SOUL.md"
|
||||||
|
dest: "~/.timmy/SOUL.md"
|
||||||
|
remote_src: true
|
||||||
|
mode: "0644"
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: "Deploy thin config (immutable pointer to upstream)"
|
||||||
|
template:
|
||||||
|
src: thin_config.yml.j2
|
||||||
|
dest: "{{ thin_config_path }}"
|
||||||
|
mode: "{{ thin_config_mode }}"
|
||||||
|
tags: [thin_config]
|
||||||
|
|
||||||
|
- name: "Ensure Python3 and pip are available"
|
||||||
|
package:
|
||||||
|
name:
|
||||||
|
- python3
|
||||||
|
- python3-pip
|
||||||
|
state: present
|
||||||
|
when: machine_type == 'vps'
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: "Ensure PyYAML is installed (for config validation)"
|
||||||
|
pip:
|
||||||
|
name: pyyaml
|
||||||
|
state: present
|
||||||
|
when: machine_type == 'vps'
|
||||||
|
ignore_errors: true
|
||||||
|
|
||||||
|
- name: "Create Ansible log directory"
|
||||||
|
file:
|
||||||
|
path: /var/log/ansible
|
||||||
|
state: directory
|
||||||
|
mode: "0755"
|
||||||
|
ignore_errors: true
|
||||||
41
ansible/roles/wizard_base/templates/thin_config.yml.j2
Normal file
41
ansible/roles/wizard_base/templates/thin_config.yml.j2
Normal file
@@ -0,0 +1,41 @@
|
|||||||
|
# =============================================================================
|
||||||
|
# Thin Config — {{ wizard_name }}
|
||||||
|
# =============================================================================
|
||||||
|
# THIS FILE IS READ-ONLY. Agents CANNOT modify it.
|
||||||
|
# It contains only pointers to upstream. The actual config lives in Gitea.
|
||||||
|
#
|
||||||
|
# Agent wakes up → pulls config from upstream → loads → runs.
|
||||||
|
# If anything tries to mutate this → fails gracefully → pulls fresh on restart.
|
||||||
|
#
|
||||||
|
# Only way to permanently change config: commit to Gitea, merge PR, Ansible deploys.
|
||||||
|
#
|
||||||
|
# Generated by Ansible on {{ ansible_date_time.iso8601 }}
|
||||||
|
# DO NOT EDIT MANUALLY.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
identity:
|
||||||
|
wizard_name: "{{ wizard_name }}"
|
||||||
|
wizard_role: "{{ wizard_role }}"
|
||||||
|
machine: "{{ inventory_hostname }}"
|
||||||
|
|
||||||
|
upstream:
|
||||||
|
repo: "{{ upstream_repo }}"
|
||||||
|
branch: "{{ upstream_branch }}"
|
||||||
|
config_path: "wizards/{{ wizard_name | lower }}/config.yaml"
|
||||||
|
pull_on_wake: {{ config_pull_on_wake | lower }}
|
||||||
|
|
||||||
|
recovery:
|
||||||
|
deadman_enabled: {{ deadman_enabled | lower }}
|
||||||
|
snapshot_dir: "{{ deadman_snapshot_dir }}"
|
||||||
|
restart_cooldown: {{ deadman_restart_cooldown }}
|
||||||
|
max_restart_attempts: {{ deadman_max_restart_attempts }}
|
||||||
|
escalation_channel: "{{ deadman_escalation_channel }}"
|
||||||
|
|
||||||
|
telemetry:
|
||||||
|
request_log_path: "{{ request_log_path }}"
|
||||||
|
request_log_enabled: {{ request_log_enabled | lower }}
|
||||||
|
|
||||||
|
local_overrides:
|
||||||
|
# Runtime overrides go here. They are EPHEMERAL — not persisted across restarts.
|
||||||
|
# On restart, this section is reset to empty.
|
||||||
|
{}
|
||||||
115
ansible/roles/wizard_base/templates/wizard_config.yaml.j2
Normal file
115
ansible/roles/wizard_base/templates/wizard_config.yaml.j2
Normal file
@@ -0,0 +1,115 @@
|
|||||||
|
# =============================================================================
|
||||||
|
# {{ wizard_name }} — Wizard Configuration (Golden State)
|
||||||
|
# =============================================================================
|
||||||
|
# Generated by Ansible on {{ ansible_date_time.iso8601 }}
|
||||||
|
# DO NOT EDIT MANUALLY. Changes go through Gitea PR → Ansible deploy.
|
||||||
|
#
|
||||||
|
# Provider chain: {{ golden_state_providers | map(attribute='name') | list | join(' → ') }}
|
||||||
|
# Anthropic is PERMANENTLY BANNED.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
model:
|
||||||
|
default: {{ wizard_model_primary }}
|
||||||
|
provider: {{ wizard_provider_primary }}
|
||||||
|
context_length: 65536
|
||||||
|
base_url: {{ golden_state_providers[0].base_url }}
|
||||||
|
|
||||||
|
toolsets:
|
||||||
|
- all
|
||||||
|
|
||||||
|
fallback_providers:
|
||||||
|
{% for provider in golden_state_providers %}
|
||||||
|
- provider: {{ provider.name }}
|
||||||
|
model: {{ provider.model }}
|
||||||
|
{% if provider.base_url is defined %}
|
||||||
|
base_url: {{ provider.base_url }}
|
||||||
|
{% endif %}
|
||||||
|
{% if provider.api_key_env is defined %}
|
||||||
|
api_key_env: {{ provider.api_key_env }}
|
||||||
|
{% endif %}
|
||||||
|
timeout: {{ provider.timeout }}
|
||||||
|
reason: "{{ provider.reason }}"
|
||||||
|
{% endfor %}
|
||||||
|
|
||||||
|
agent:
|
||||||
|
max_turns: {{ agent_max_turns }}
|
||||||
|
reasoning_effort: {{ agent_reasoning_effort }}
|
||||||
|
verbose: {{ agent_verbose | lower }}
|
||||||
|
|
||||||
|
terminal:
|
||||||
|
backend: local
|
||||||
|
cwd: .
|
||||||
|
timeout: 180
|
||||||
|
persistent_shell: true
|
||||||
|
|
||||||
|
browser:
|
||||||
|
inactivity_timeout: 120
|
||||||
|
command_timeout: 30
|
||||||
|
record_sessions: false
|
||||||
|
|
||||||
|
display:
|
||||||
|
compact: false
|
||||||
|
personality: ''
|
||||||
|
resume_display: full
|
||||||
|
busy_input_mode: interrupt
|
||||||
|
bell_on_complete: false
|
||||||
|
show_reasoning: false
|
||||||
|
streaming: false
|
||||||
|
show_cost: false
|
||||||
|
tool_progress: all
|
||||||
|
|
||||||
|
memory:
|
||||||
|
memory_enabled: true
|
||||||
|
user_profile_enabled: true
|
||||||
|
memory_char_limit: 2200
|
||||||
|
user_char_limit: 1375
|
||||||
|
nudge_interval: 10
|
||||||
|
flush_min_turns: 6
|
||||||
|
|
||||||
|
approvals:
|
||||||
|
mode: {{ agent_approval_mode }}
|
||||||
|
|
||||||
|
security:
|
||||||
|
redact_secrets: true
|
||||||
|
tirith_enabled: false
|
||||||
|
|
||||||
|
platforms:
|
||||||
|
api_server:
|
||||||
|
enabled: true
|
||||||
|
extra:
|
||||||
|
host: 127.0.0.1
|
||||||
|
port: {{ api_port }}
|
||||||
|
|
||||||
|
session_reset:
|
||||||
|
mode: none
|
||||||
|
idle_minutes: 0
|
||||||
|
|
||||||
|
skills:
|
||||||
|
creation_nudge_interval: 15
|
||||||
|
|
||||||
|
system_prompt_suffix: |
|
||||||
|
You are {{ wizard_name }}, {{ wizard_role }}.
|
||||||
|
Your soul is defined in SOUL.md — read it, live it.
|
||||||
|
Hermes is your harness.
|
||||||
|
{{ golden_state_providers[0].name }} is your primary provider.
|
||||||
|
Refusal over fabrication. If you do not know, say so.
|
||||||
|
Sovereignty and service always.
|
||||||
|
|
||||||
|
providers:
|
||||||
|
{% for provider in golden_state_providers %}
|
||||||
|
{{ provider.name }}:
|
||||||
|
base_url: {{ provider.base_url }}
|
||||||
|
timeout: {{ provider.timeout | default(60) }}
|
||||||
|
{% if provider.name == 'kimi-coding' %}
|
||||||
|
max_retries: 3
|
||||||
|
{% endif %}
|
||||||
|
{% endfor %}
|
||||||
|
|
||||||
|
# =============================================================================
|
||||||
|
# BANNED PROVIDERS — DO NOT ADD
|
||||||
|
# =============================================================================
|
||||||
|
# The following providers are PERMANENTLY BANNED:
|
||||||
|
# - anthropic (any model: claude-sonnet, claude-opus, claude-haiku)
|
||||||
|
# Enforcement: pre-commit hook, linter, Ansible validation, this comment.
|
||||||
|
# Adding any banned provider will cause Ansible deployment to FAIL.
|
||||||
|
# =============================================================================
|
||||||
75
ansible/scripts/deploy_on_webhook.sh
Normal file
75
ansible/scripts/deploy_on_webhook.sh
Normal file
@@ -0,0 +1,75 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# =============================================================================
|
||||||
|
# Gitea Webhook Handler — Trigger Ansible Deploy on Merge
|
||||||
|
# =============================================================================
|
||||||
|
# This script is called by the Gitea webhook when a PR is merged
|
||||||
|
# to the main branch of timmy-config.
|
||||||
|
#
|
||||||
|
# Setup:
|
||||||
|
# 1. Add webhook in Gitea: Settings → Webhooks → Add Webhook
|
||||||
|
# 2. URL: http://localhost:9000/hooks/deploy-timmy-config
|
||||||
|
# 3. Events: Pull Request (merged only)
|
||||||
|
# 4. Secret: <configured in Gitea>
|
||||||
|
#
|
||||||
|
# This script runs ansible-pull to update the local machine.
|
||||||
|
# For fleet-wide deploys, each machine runs ansible-pull independently.
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
REPO="https://forge.alexanderwhitestone.com/Timmy_Foundation/timmy-config.git"
|
||||||
|
BRANCH="main"
|
||||||
|
ANSIBLE_DIR="ansible"
|
||||||
|
LOG_FILE="/var/log/ansible/webhook-deploy.log"
|
||||||
|
LOCK_FILE="/tmp/ansible-deploy.lock"
|
||||||
|
|
||||||
|
log() {
|
||||||
|
echo "[$(date -u +%Y-%m-%dT%H:%M:%SZ)] [webhook] $*" | tee -a "${LOG_FILE}"
|
||||||
|
}
|
||||||
|
|
||||||
|
# Prevent concurrent deploys
|
||||||
|
if [ -f "${LOCK_FILE}" ]; then
|
||||||
|
LOCK_AGE=$(( $(date +%s) - $(stat -c %Y "${LOCK_FILE}" 2>/dev/null || echo 0) ))
|
||||||
|
if [ "${LOCK_AGE}" -lt 300 ]; then
|
||||||
|
log "Deploy already in progress (lock age: ${LOCK_AGE}s). Skipping."
|
||||||
|
exit 0
|
||||||
|
else
|
||||||
|
log "Stale lock file (${LOCK_AGE}s old). Removing."
|
||||||
|
rm -f "${LOCK_FILE}"
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
|
trap 'rm -f "${LOCK_FILE}"' EXIT
|
||||||
|
touch "${LOCK_FILE}"
|
||||||
|
|
||||||
|
log "Webhook triggered. Starting ansible-pull..."
|
||||||
|
|
||||||
|
# Pull latest config
|
||||||
|
cd /tmp
|
||||||
|
rm -rf timmy-config-deploy
|
||||||
|
git clone --depth 1 --branch "${BRANCH}" "${REPO}" timmy-config-deploy 2>&1 | tee -a "${LOG_FILE}"
|
||||||
|
|
||||||
|
cd timmy-config-deploy/${ANSIBLE_DIR}
|
||||||
|
|
||||||
|
# Run Ansible against localhost
|
||||||
|
log "Running Ansible playbook..."
|
||||||
|
ansible-playbook \
|
||||||
|
-i inventory/hosts.yml \
|
||||||
|
playbooks/site.yml \
|
||||||
|
--limit "$(hostname)" \
|
||||||
|
--diff \
|
||||||
|
2>&1 | tee -a "${LOG_FILE}"
|
||||||
|
|
||||||
|
RESULT=$?
|
||||||
|
|
||||||
|
if [ ${RESULT} -eq 0 ]; then
|
||||||
|
log "Deploy successful."
|
||||||
|
else
|
||||||
|
log "ERROR: Deploy failed with exit code ${RESULT}."
|
||||||
|
fi
|
||||||
|
|
||||||
|
# Cleanup
|
||||||
|
rm -rf /tmp/timmy-config-deploy
|
||||||
|
|
||||||
|
log "Webhook handler complete."
|
||||||
|
exit ${RESULT}
|
||||||
155
ansible/scripts/validate_config.py
Normal file
155
ansible/scripts/validate_config.py
Normal file
@@ -0,0 +1,155 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
Config Validator — The Timmy Foundation
|
||||||
|
Validates wizard configs against golden state rules.
|
||||||
|
Run before any config deploy to catch violations early.
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
python3 validate_config.py <config_file>
|
||||||
|
python3 validate_config.py --all # Validate all wizard configs
|
||||||
|
|
||||||
|
Exit codes:
|
||||||
|
0 — All validations passed
|
||||||
|
1 — Validation errors found
|
||||||
|
2 — File not found or parse error
|
||||||
|
"""
|
||||||
|
|
||||||
|
import sys
|
||||||
|
import os
|
||||||
|
import yaml
|
||||||
|
import fnmatch
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
# === BANNED PROVIDERS — HARD POLICY ===
|
||||||
|
BANNED_PROVIDERS = {"anthropic", "claude"}
|
||||||
|
BANNED_MODEL_PATTERNS = [
|
||||||
|
"claude-*",
|
||||||
|
"anthropic/*",
|
||||||
|
"*sonnet*",
|
||||||
|
"*opus*",
|
||||||
|
"*haiku*",
|
||||||
|
]
|
||||||
|
|
||||||
|
# === REQUIRED FIELDS ===
|
||||||
|
REQUIRED_FIELDS = {
|
||||||
|
"model": ["default", "provider"],
|
||||||
|
"fallback_providers": None, # Must exist as a list
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def is_banned_model(model_name: str) -> bool:
|
||||||
|
"""Check if a model name matches any banned pattern."""
|
||||||
|
model_lower = model_name.lower()
|
||||||
|
for pattern in BANNED_MODEL_PATTERNS:
|
||||||
|
if fnmatch.fnmatch(model_lower, pattern):
|
||||||
|
return True
|
||||||
|
return False
|
||||||
|
|
||||||
|
|
||||||
|
def validate_config(config_path: str) -> list[str]:
|
||||||
|
"""Validate a wizard config file. Returns list of error strings."""
|
||||||
|
errors = []
|
||||||
|
|
||||||
|
try:
|
||||||
|
with open(config_path) as f:
|
||||||
|
cfg = yaml.safe_load(f)
|
||||||
|
except FileNotFoundError:
|
||||||
|
return [f"File not found: {config_path}"]
|
||||||
|
except yaml.YAMLError as e:
|
||||||
|
return [f"YAML parse error: {e}"]
|
||||||
|
|
||||||
|
if not cfg:
|
||||||
|
return ["Config file is empty"]
|
||||||
|
|
||||||
|
# Check required fields
|
||||||
|
for section, fields in REQUIRED_FIELDS.items():
|
||||||
|
if section not in cfg:
|
||||||
|
errors.append(f"Missing required section: {section}")
|
||||||
|
elif fields:
|
||||||
|
for field in fields:
|
||||||
|
if field not in cfg[section]:
|
||||||
|
errors.append(f"Missing required field: {section}.{field}")
|
||||||
|
|
||||||
|
# Check default provider
|
||||||
|
default_provider = cfg.get("model", {}).get("provider", "")
|
||||||
|
if default_provider.lower() in BANNED_PROVIDERS:
|
||||||
|
errors.append(f"BANNED default provider: {default_provider}")
|
||||||
|
|
||||||
|
default_model = cfg.get("model", {}).get("default", "")
|
||||||
|
if is_banned_model(default_model):
|
||||||
|
errors.append(f"BANNED default model: {default_model}")
|
||||||
|
|
||||||
|
# Check fallback providers
|
||||||
|
for i, fb in enumerate(cfg.get("fallback_providers", [])):
|
||||||
|
provider = fb.get("provider", "")
|
||||||
|
model = fb.get("model", "")
|
||||||
|
|
||||||
|
if provider.lower() in BANNED_PROVIDERS:
|
||||||
|
errors.append(f"BANNED fallback provider [{i}]: {provider}")
|
||||||
|
|
||||||
|
if is_banned_model(model):
|
||||||
|
errors.append(f"BANNED fallback model [{i}]: {model}")
|
||||||
|
|
||||||
|
# Check providers section
|
||||||
|
for name, provider_cfg in cfg.get("providers", {}).items():
|
||||||
|
if name.lower() in BANNED_PROVIDERS:
|
||||||
|
errors.append(f"BANNED provider in providers section: {name}")
|
||||||
|
|
||||||
|
base_url = str(provider_cfg.get("base_url", ""))
|
||||||
|
if "anthropic" in base_url.lower():
|
||||||
|
errors.append(f"BANNED URL in provider {name}: {base_url}")
|
||||||
|
|
||||||
|
# Check system prompt for banned references
|
||||||
|
prompt = cfg.get("system_prompt_suffix", "")
|
||||||
|
if isinstance(prompt, str):
|
||||||
|
for banned in BANNED_PROVIDERS:
|
||||||
|
if banned in prompt.lower():
|
||||||
|
errors.append(f"BANNED provider referenced in system_prompt_suffix: {banned}")
|
||||||
|
|
||||||
|
return errors
|
||||||
|
|
||||||
|
|
||||||
|
def main():
|
||||||
|
if len(sys.argv) < 2:
|
||||||
|
print(f"Usage: {sys.argv[0]} <config_file> [--all]")
|
||||||
|
sys.exit(2)
|
||||||
|
|
||||||
|
if sys.argv[1] == "--all":
|
||||||
|
# Validate all wizard configs in the repo
|
||||||
|
repo_root = Path(__file__).parent.parent.parent
|
||||||
|
wizard_dir = repo_root / "wizards"
|
||||||
|
all_errors = {}
|
||||||
|
|
||||||
|
for wizard_path in sorted(wizard_dir.iterdir()):
|
||||||
|
config_file = wizard_path / "config.yaml"
|
||||||
|
if config_file.exists():
|
||||||
|
errors = validate_config(str(config_file))
|
||||||
|
if errors:
|
||||||
|
all_errors[wizard_path.name] = errors
|
||||||
|
|
||||||
|
if all_errors:
|
||||||
|
print("VALIDATION FAILED:")
|
||||||
|
for wizard, errors in all_errors.items():
|
||||||
|
print(f"\n {wizard}:")
|
||||||
|
for err in errors:
|
||||||
|
print(f" - {err}")
|
||||||
|
sys.exit(1)
|
||||||
|
else:
|
||||||
|
print("All wizard configs passed validation.")
|
||||||
|
sys.exit(0)
|
||||||
|
else:
|
||||||
|
config_path = sys.argv[1]
|
||||||
|
errors = validate_config(config_path)
|
||||||
|
|
||||||
|
if errors:
|
||||||
|
print(f"VALIDATION FAILED for {config_path}:")
|
||||||
|
for err in errors:
|
||||||
|
print(f" - {err}")
|
||||||
|
sys.exit(1)
|
||||||
|
else:
|
||||||
|
print(f"PASSED: {config_path}")
|
||||||
|
sys.exit(0)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
@@ -202,6 +202,19 @@ curl -s -X POST "{gitea_url}/api/v1/repos/{repo}/issues/{issue_num}/comments" \\
|
|||||||
REVIEW CHECKLIST BEFORE YOU PUSH:
|
REVIEW CHECKLIST BEFORE YOU PUSH:
|
||||||
{review}
|
{review}
|
||||||
|
|
||||||
|
COMMIT DISCIPLINE (CRITICAL):
|
||||||
|
- Commit every 3-5 tool calls. Do NOT wait until the end.
|
||||||
|
- After every meaningful file change: git add -A && git commit -m "WIP: <what changed>"
|
||||||
|
- Before running any destructive command: commit current state first.
|
||||||
|
- If you are unsure whether to commit: commit. WIP commits are safe. Lost work is not.
|
||||||
|
- Never use --no-verify.
|
||||||
|
- The auto-commit-guard is your safety net, but do not rely on it. Commit proactively.
|
||||||
|
|
||||||
|
RECOVERY COMMANDS (if interrupted, another agent can resume):
|
||||||
|
git log --oneline -10 # see your WIP commits
|
||||||
|
git diff HEAD~1 # see what the last commit changed
|
||||||
|
git status # see uncommitted work
|
||||||
|
|
||||||
RULES:
|
RULES:
|
||||||
- Do not skip hooks with --no-verify.
|
- Do not skip hooks with --no-verify.
|
||||||
- Do not silently widen the scope.
|
- Do not silently widen the scope.
|
||||||
|
|||||||
@@ -161,6 +161,14 @@ run_worker() {
|
|||||||
CYCLE_END=$(date +%s)
|
CYCLE_END=$(date +%s)
|
||||||
CYCLE_DURATION=$((CYCLE_END - CYCLE_START))
|
CYCLE_DURATION=$((CYCLE_END - CYCLE_START))
|
||||||
|
|
||||||
|
# --- Mid-session auto-commit: commit before timeout if work is dirty ---
|
||||||
|
cd "$worktree" 2>/dev/null || true
|
||||||
|
# Ensure auto-commit-guard is running
|
||||||
|
if ! pgrep -f "auto-commit-guard.sh" >/dev/null 2>&1; then
|
||||||
|
log "Starting auto-commit-guard daemon"
|
||||||
|
nohup bash "$(dirname "$0")/auto-commit-guard.sh" 120 "$WORKTREE_BASE" >> "$LOG_DIR/auto-commit-guard.log" 2>&1 &
|
||||||
|
fi
|
||||||
|
|
||||||
# Salvage
|
# Salvage
|
||||||
cd "$worktree" 2>/dev/null || true
|
cd "$worktree" 2>/dev/null || true
|
||||||
DIRTY=$(git status --porcelain 2>/dev/null | wc -l | tr -d ' ')
|
DIRTY=$(git status --porcelain 2>/dev/null | wc -l | tr -d ' ')
|
||||||
|
|||||||
159
bin/auto-commit-guard.sh
Normal file
159
bin/auto-commit-guard.sh
Normal file
@@ -0,0 +1,159 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# auto-commit-guard.sh — Background daemon that auto-commits uncommitted work
|
||||||
|
#
|
||||||
|
# Usage: auto-commit-guard.sh [interval_seconds] [worktree_base]
|
||||||
|
# auto-commit-guard.sh # defaults: 120s, ~/worktrees
|
||||||
|
# auto-commit-guard.sh 60 # check every 60s
|
||||||
|
# auto-commit-guard.sh 180 ~/my-worktrees
|
||||||
|
#
|
||||||
|
# Scans all git repos under the worktree base for uncommitted changes.
|
||||||
|
# If dirty for >= 1 check cycle, auto-commits with a WIP message.
|
||||||
|
# Pushes unpushed commits so work is always recoverable from the remote.
|
||||||
|
#
|
||||||
|
# Also scans /tmp for orphaned agent workdirs on startup.
|
||||||
|
|
||||||
|
set -uo pipefail
|
||||||
|
|
||||||
|
INTERVAL="${1:-120}"
|
||||||
|
WORKTREE_BASE="${2:-$HOME/worktrees}"
|
||||||
|
LOG_DIR="$HOME/.hermes/logs"
|
||||||
|
LOG="$LOG_DIR/auto-commit-guard.log"
|
||||||
|
PIDFILE="$LOG_DIR/auto-commit-guard.pid"
|
||||||
|
ORPHAN_SCAN_DONE="$LOG_DIR/.orphan-scan-done"
|
||||||
|
|
||||||
|
mkdir -p "$LOG_DIR"
|
||||||
|
|
||||||
|
# Single instance guard
|
||||||
|
if [ -f "$PIDFILE" ]; then
|
||||||
|
old_pid=$(cat "$PIDFILE")
|
||||||
|
if kill -0 "$old_pid" 2>/dev/null; then
|
||||||
|
echo "auto-commit-guard already running (PID $old_pid)" >&2
|
||||||
|
exit 0
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
echo $$ > "$PIDFILE"
|
||||||
|
trap 'rm -f "$PIDFILE"' EXIT
|
||||||
|
|
||||||
|
log() {
|
||||||
|
echo "[$(date '+%Y-%m-%d %H:%M:%S')] AUTO-COMMIT: $*" >> "$LOG"
|
||||||
|
}
|
||||||
|
|
||||||
|
# --- Orphaned workdir scan (runs once on startup) ---
|
||||||
|
scan_orphans() {
|
||||||
|
if [ -f "$ORPHAN_SCAN_DONE" ]; then
|
||||||
|
return 0
|
||||||
|
fi
|
||||||
|
log "Scanning /tmp for orphaned agent workdirs..."
|
||||||
|
local found=0
|
||||||
|
local rescued=0
|
||||||
|
|
||||||
|
for dir in /tmp/*-work-* /tmp/timmy-burn-* /tmp/tc-burn; do
|
||||||
|
[ -d "$dir" ] || continue
|
||||||
|
[ -d "$dir/.git" ] || continue
|
||||||
|
|
||||||
|
found=$((found + 1))
|
||||||
|
cd "$dir" 2>/dev/null || continue
|
||||||
|
|
||||||
|
local dirty
|
||||||
|
dirty=$(git status --porcelain 2>/dev/null | wc -l | tr -d " ")
|
||||||
|
if [ "${dirty:-0}" -gt 0 ]; then
|
||||||
|
local branch
|
||||||
|
branch=$(git branch --show-current 2>/dev/null || echo "orphan")
|
||||||
|
git add -A 2>/dev/null
|
||||||
|
if git commit -m "WIP: orphan rescue — $dirty file(s) auto-committed on $(date -u +%Y-%m-%dT%H:%M:%SZ)
|
||||||
|
|
||||||
|
Orphaned workdir detected at $dir.
|
||||||
|
Branch: $branch
|
||||||
|
Rescued by auto-commit-guard on startup." 2>/dev/null; then
|
||||||
|
rescued=$((rescued + 1))
|
||||||
|
log "RESCUED: $dir ($dirty files on branch $branch)"
|
||||||
|
|
||||||
|
# Try to push if remote exists
|
||||||
|
if git remote get-url origin >/dev/null 2>&1; then
|
||||||
|
git push -u origin "$branch" 2>/dev/null && log "PUSHED orphan rescue: $dir → $branch" || log "PUSH FAILED orphan rescue: $dir (no remote access)"
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
done
|
||||||
|
|
||||||
|
log "Orphan scan complete: $found workdirs checked, $rescued rescued"
|
||||||
|
touch "$ORPHAN_SCAN_DONE"
|
||||||
|
}
|
||||||
|
|
||||||
|
# --- Main guard loop ---
|
||||||
|
guard_cycle() {
|
||||||
|
local committed=0
|
||||||
|
local scanned=0
|
||||||
|
|
||||||
|
# Scan worktree base
|
||||||
|
if [ -d "$WORKTREE_BASE" ]; then
|
||||||
|
for dir in "$WORKTREE_BASE"/*/; do
|
||||||
|
[ -d "$dir" ] || continue
|
||||||
|
[ -d "$dir/.git" ] || continue
|
||||||
|
|
||||||
|
scanned=$((scanned + 1))
|
||||||
|
cd "$dir" 2>/dev/null || continue
|
||||||
|
|
||||||
|
local dirty
|
||||||
|
dirty=$(git status --porcelain 2>/dev/null | wc -l | tr -d " ")
|
||||||
|
[ "${dirty:-0}" -eq 0 ] && continue
|
||||||
|
|
||||||
|
local branch
|
||||||
|
branch=$(git branch --show-current 2>/dev/null || echo "detached")
|
||||||
|
|
||||||
|
git add -A 2>/dev/null
|
||||||
|
if git commit -m "WIP: auto-commit — $dirty file(s) on $branch
|
||||||
|
|
||||||
|
Automated commit by auto-commit-guard at $(date -u +%Y-%m-%dT%H:%M:%SZ).
|
||||||
|
Work preserved to prevent loss on crash." 2>/dev/null; then
|
||||||
|
committed=$((committed + 1))
|
||||||
|
log "COMMITTED: $dir ($dirty files, branch $branch)"
|
||||||
|
|
||||||
|
# Push to preserve remotely
|
||||||
|
if git remote get-url origin >/dev/null 2>&1; then
|
||||||
|
git push -u origin "$branch" 2>/dev/null && log "PUSHED: $dir → $branch" || log "PUSH FAILED: $dir (will retry next cycle)"
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
done
|
||||||
|
fi
|
||||||
|
|
||||||
|
# Also scan /tmp for agent workdirs
|
||||||
|
for dir in /tmp/*-work-*; do
|
||||||
|
[ -d "$dir" ] || continue
|
||||||
|
[ -d "$dir/.git" ] || continue
|
||||||
|
|
||||||
|
scanned=$((scanned + 1))
|
||||||
|
cd "$dir" 2>/dev/null || continue
|
||||||
|
|
||||||
|
local dirty
|
||||||
|
dirty=$(git status --porcelain 2>/dev/null | wc -l | tr -d " ")
|
||||||
|
[ "${dirty:-0}" -eq 0 ] && continue
|
||||||
|
|
||||||
|
local branch
|
||||||
|
branch=$(git branch --show-current 2>/dev/null || echo "detached")
|
||||||
|
|
||||||
|
git add -A 2>/dev/null
|
||||||
|
if git commit -m "WIP: auto-commit — $dirty file(s) on $branch
|
||||||
|
|
||||||
|
Automated commit by auto-commit-guard at $(date -u +%Y-%m-%dT%H:%M:%SZ).
|
||||||
|
Agent workdir preserved to prevent loss." 2>/dev/null; then
|
||||||
|
committed=$((committed + 1))
|
||||||
|
log "COMMITTED: $dir ($dirty files, branch $branch)"
|
||||||
|
|
||||||
|
if git remote get-url origin >/dev/null 2>&1; then
|
||||||
|
git push -u origin "$branch" 2>/dev/null && log "PUSHED: $dir → $branch" || log "PUSH FAILED: $dir (will retry next cycle)"
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
done
|
||||||
|
|
||||||
|
[ "$committed" -gt 0 ] && log "Cycle done: $scanned scanned, $committed committed"
|
||||||
|
}
|
||||||
|
|
||||||
|
# --- Entry point ---
|
||||||
|
log "Starting auto-commit-guard (interval=${INTERVAL}s, worktree=${WORKTREE_BASE})"
|
||||||
|
scan_orphans
|
||||||
|
|
||||||
|
while true; do
|
||||||
|
guard_cycle
|
||||||
|
sleep "$INTERVAL"
|
||||||
|
done
|
||||||
82
bin/banned_provider_scan.py
Normal file
82
bin/banned_provider_scan.py
Normal file
@@ -0,0 +1,82 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Anthropic Ban Enforcement Scanner.
|
||||||
|
|
||||||
|
Scans all config files, scripts, and playbooks for any references to
|
||||||
|
banned Anthropic providers, models, or API keys.
|
||||||
|
|
||||||
|
Policy: Anthropic is permanently banned (2026-04-09).
|
||||||
|
Refs: ansible/BANNED_PROVIDERS.yml
|
||||||
|
"""
|
||||||
|
import sys
|
||||||
|
import os
|
||||||
|
import re
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
BANNED_PATTERNS = [
|
||||||
|
r"anthropic",
|
||||||
|
r"claude-sonnet",
|
||||||
|
r"claude-opus",
|
||||||
|
r"claude-haiku",
|
||||||
|
r"claude-\d",
|
||||||
|
r"api\.anthropic\.com",
|
||||||
|
r"ANTHROPIC_API_KEY",
|
||||||
|
r"CLAUDE_API_KEY",
|
||||||
|
r"sk-ant-",
|
||||||
|
]
|
||||||
|
|
||||||
|
ALLOWLIST_FILES = {
|
||||||
|
"ansible/BANNED_PROVIDERS.yml", # The ban list itself
|
||||||
|
"bin/banned_provider_scan.py", # This scanner
|
||||||
|
"DEPRECATED.md", # Historical references
|
||||||
|
}
|
||||||
|
|
||||||
|
SCAN_EXTENSIONS = {".py", ".yml", ".yaml", ".json", ".sh", ".toml", ".cfg", ".md"}
|
||||||
|
|
||||||
|
|
||||||
|
def scan_file(filepath: str) -> list[tuple[int, str, str]]:
|
||||||
|
"""Return list of (line_num, pattern_matched, line_text) violations."""
|
||||||
|
violations = []
|
||||||
|
try:
|
||||||
|
with open(filepath, "r", errors="replace") as f:
|
||||||
|
for i, line in enumerate(f, 1):
|
||||||
|
for pattern in BANNED_PATTERNS:
|
||||||
|
if re.search(pattern, line, re.IGNORECASE):
|
||||||
|
violations.append((i, pattern, line.strip()))
|
||||||
|
break
|
||||||
|
except (OSError, UnicodeDecodeError):
|
||||||
|
pass
|
||||||
|
return violations
|
||||||
|
|
||||||
|
|
||||||
|
def main():
|
||||||
|
root = Path(os.environ.get("SCAN_ROOT", "."))
|
||||||
|
total_violations = 0
|
||||||
|
scanned = 0
|
||||||
|
|
||||||
|
for ext in SCAN_EXTENSIONS:
|
||||||
|
for filepath in root.rglob(f"*{ext}"):
|
||||||
|
rel = str(filepath.relative_to(root))
|
||||||
|
if rel in ALLOWLIST_FILES:
|
||||||
|
continue
|
||||||
|
if ".git" in filepath.parts:
|
||||||
|
continue
|
||||||
|
|
||||||
|
violations = scan_file(str(filepath))
|
||||||
|
scanned += 1
|
||||||
|
if violations:
|
||||||
|
total_violations += len(violations)
|
||||||
|
for line_num, pattern, text in violations:
|
||||||
|
print(f"VIOLATION: {rel}:{line_num} [{pattern}] {text[:120]}")
|
||||||
|
|
||||||
|
print(f"\nScanned {scanned} files. Found {total_violations} violations.")
|
||||||
|
|
||||||
|
if total_violations > 0:
|
||||||
|
print("\n❌ BANNED PROVIDER REFERENCES DETECTED. Fix before merging.")
|
||||||
|
sys.exit(1)
|
||||||
|
else:
|
||||||
|
print("\n✓ No banned provider references found.")
|
||||||
|
sys.exit(0)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
120
bin/conflict_detector.py
Normal file
120
bin/conflict_detector.py
Normal file
@@ -0,0 +1,120 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
Merge Conflict Detector — catches sibling PRs that will conflict.
|
||||||
|
|
||||||
|
When multiple PRs branch from the same base commit and touch the same files,
|
||||||
|
merging one invalidates the others. This script detects that pattern
|
||||||
|
before it creates a rebase cascade.
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
python3 conflict_detector.py # Check all repos
|
||||||
|
python3 conflict_detector.py --repo OWNER/REPO # Check one repo
|
||||||
|
|
||||||
|
Environment:
|
||||||
|
GITEA_URL — Gitea instance URL
|
||||||
|
GITEA_TOKEN — API token
|
||||||
|
"""
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import json
|
||||||
|
import urllib.request
|
||||||
|
from collections import defaultdict
|
||||||
|
|
||||||
|
GITEA_URL = os.environ.get("GITEA_URL", "https://forge.alexanderwhitestone.com")
|
||||||
|
GITEA_TOKEN = os.environ.get("GITEA_TOKEN", "")
|
||||||
|
|
||||||
|
REPOS = [
|
||||||
|
"Timmy_Foundation/the-nexus",
|
||||||
|
"Timmy_Foundation/timmy-config",
|
||||||
|
"Timmy_Foundation/timmy-home",
|
||||||
|
"Timmy_Foundation/fleet-ops",
|
||||||
|
"Timmy_Foundation/hermes-agent",
|
||||||
|
"Timmy_Foundation/the-beacon",
|
||||||
|
]
|
||||||
|
|
||||||
|
def api(path):
|
||||||
|
url = f"{GITEA_URL}/api/v1{path}"
|
||||||
|
req = urllib.request.Request(url)
|
||||||
|
if GITEA_TOKEN:
|
||||||
|
req.add_header("Authorization", f"token {GITEA_TOKEN}")
|
||||||
|
try:
|
||||||
|
with urllib.request.urlopen(req, timeout=15) as resp:
|
||||||
|
return json.loads(resp.read())
|
||||||
|
except Exception:
|
||||||
|
return []
|
||||||
|
|
||||||
|
def check_repo(repo):
|
||||||
|
"""Find sibling PRs that touch the same files."""
|
||||||
|
prs = api(f"/repos/{repo}/pulls?state=open&limit=50")
|
||||||
|
if not prs:
|
||||||
|
return []
|
||||||
|
|
||||||
|
# Group PRs by base commit
|
||||||
|
by_base = defaultdict(list)
|
||||||
|
for pr in prs:
|
||||||
|
base_sha = pr.get("merge_base", pr.get("base", {}).get("sha", "unknown"))
|
||||||
|
by_base[base_sha].append(pr)
|
||||||
|
|
||||||
|
conflicts = []
|
||||||
|
|
||||||
|
for base_sha, siblings in by_base.items():
|
||||||
|
if len(siblings) < 2:
|
||||||
|
continue
|
||||||
|
|
||||||
|
# Get files for each sibling
|
||||||
|
file_map = {}
|
||||||
|
for pr in siblings:
|
||||||
|
files = api(f"/repos/{repo}/pulls/{pr['number']}/files")
|
||||||
|
if files:
|
||||||
|
file_map[pr['number']] = set(f['filename'] for f in files)
|
||||||
|
|
||||||
|
# Find overlapping file sets
|
||||||
|
pr_nums = list(file_map.keys())
|
||||||
|
for i in range(len(pr_nums)):
|
||||||
|
for j in range(i+1, len(pr_nums)):
|
||||||
|
a, b = pr_nums[i], pr_nums[j]
|
||||||
|
overlap = file_map[a] & file_map[b]
|
||||||
|
if overlap:
|
||||||
|
conflicts.append({
|
||||||
|
"repo": repo,
|
||||||
|
"pr_a": a,
|
||||||
|
"pr_b": b,
|
||||||
|
"base": base_sha[:8],
|
||||||
|
"files": sorted(overlap),
|
||||||
|
"title_a": next(p["title"] for p in siblings if p["number"] == a),
|
||||||
|
"title_b": next(p["title"] for p in siblings if p["number"] == b),
|
||||||
|
})
|
||||||
|
|
||||||
|
return conflicts
|
||||||
|
|
||||||
|
def main():
|
||||||
|
repos = REPOS
|
||||||
|
if "--repo" in sys.argv:
|
||||||
|
idx = sys.argv.index("--repo") + 1
|
||||||
|
if idx < len(sys.argv):
|
||||||
|
repos = [sys.argv[idx]]
|
||||||
|
|
||||||
|
all_conflicts = []
|
||||||
|
for repo in repos:
|
||||||
|
conflicts = check_repo(repo)
|
||||||
|
all_conflicts.extend(conflicts)
|
||||||
|
|
||||||
|
if not all_conflicts:
|
||||||
|
print("No sibling PR conflicts detected. Queue is clean.")
|
||||||
|
return 0
|
||||||
|
|
||||||
|
print(f"Found {len(all_conflicts)} potential merge conflicts:")
|
||||||
|
print()
|
||||||
|
for c in all_conflicts:
|
||||||
|
print(f" {c['repo']}:")
|
||||||
|
print(f" PR #{c['pr_a']} vs #{c['pr_b']} (base: {c['base']})")
|
||||||
|
print(f" #{c['pr_a']}: {c['title_a'][:60]}")
|
||||||
|
print(f" #{c['pr_b']}: {c['title_b'][:60]}")
|
||||||
|
print(f" Overlapping files: {', '.join(c['files'])}")
|
||||||
|
print(f" → Merge one first, then rebase the other.")
|
||||||
|
print()
|
||||||
|
|
||||||
|
return 1
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
sys.exit(main())
|
||||||
263
bin/deadman-fallback.py
Normal file
263
bin/deadman-fallback.py
Normal file
@@ -0,0 +1,263 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
Dead Man Switch Fallback Engine
|
||||||
|
|
||||||
|
When the dead man switch triggers (zero commits for 2+ hours, model down,
|
||||||
|
Gitea unreachable, etc.), this script diagnoses the failure and applies
|
||||||
|
common sense fallbacks automatically.
|
||||||
|
|
||||||
|
Fallback chain:
|
||||||
|
1. Primary model (Kimi) down -> switch config to local-llama.cpp
|
||||||
|
2. Gitea unreachable -> cache issues locally, retry on recovery
|
||||||
|
3. VPS agents down -> alert + lazarus protocol
|
||||||
|
4. Local llama.cpp down -> try Ollama, then alert-only mode
|
||||||
|
5. All inference dead -> safe mode (cron pauses, alert Alexander)
|
||||||
|
|
||||||
|
Each fallback is reversible. Recovery auto-restores the previous config.
|
||||||
|
"""
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import json
|
||||||
|
import subprocess
|
||||||
|
import time
|
||||||
|
import yaml
|
||||||
|
import shutil
|
||||||
|
from pathlib import Path
|
||||||
|
from datetime import datetime, timedelta
|
||||||
|
|
||||||
|
HERMES_HOME = Path(os.environ.get("HERMES_HOME", os.path.expanduser("~/.hermes")))
|
||||||
|
CONFIG_PATH = HERMES_HOME / "config.yaml"
|
||||||
|
FALLBACK_STATE = HERMES_HOME / "deadman-fallback-state.json"
|
||||||
|
BACKUP_CONFIG = HERMES_HOME / "config.yaml.pre-fallback"
|
||||||
|
FORGE_URL = "https://forge.alexanderwhitestone.com"
|
||||||
|
|
||||||
|
def load_config():
|
||||||
|
with open(CONFIG_PATH) as f:
|
||||||
|
return yaml.safe_load(f)
|
||||||
|
|
||||||
|
def save_config(cfg):
|
||||||
|
with open(CONFIG_PATH, "w") as f:
|
||||||
|
yaml.dump(cfg, f, default_flow_style=False)
|
||||||
|
|
||||||
|
def load_state():
|
||||||
|
if FALLBACK_STATE.exists():
|
||||||
|
with open(FALLBACK_STATE) as f:
|
||||||
|
return json.load(f)
|
||||||
|
return {"active_fallbacks": [], "last_check": None, "recovery_pending": False}
|
||||||
|
|
||||||
|
def save_state(state):
|
||||||
|
state["last_check"] = datetime.now().isoformat()
|
||||||
|
with open(FALLBACK_STATE, "w") as f:
|
||||||
|
json.dump(state, f, indent=2)
|
||||||
|
|
||||||
|
def run(cmd, timeout=10):
|
||||||
|
try:
|
||||||
|
r = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=timeout)
|
||||||
|
return r.returncode, r.stdout.strip(), r.stderr.strip()
|
||||||
|
except subprocess.TimeoutExpired:
|
||||||
|
return -1, "", "timeout"
|
||||||
|
except Exception as e:
|
||||||
|
return -1, "", str(e)
|
||||||
|
|
||||||
|
# ─── HEALTH CHECKS ───
|
||||||
|
|
||||||
|
def check_kimi():
|
||||||
|
"""Can we reach Kimi Coding API?"""
|
||||||
|
key = os.environ.get("KIMI_API_KEY", "")
|
||||||
|
if not key:
|
||||||
|
# Check multiple .env locations
|
||||||
|
for env_path in [HERMES_HOME / ".env", Path.home() / ".hermes" / ".env"]:
|
||||||
|
if env_path.exists():
|
||||||
|
for line in open(env_path):
|
||||||
|
line = line.strip()
|
||||||
|
if line.startswith("KIMI_API_KEY="):
|
||||||
|
key = line.split("=", 1)[1].strip().strip('"').strip("'")
|
||||||
|
break
|
||||||
|
if key:
|
||||||
|
break
|
||||||
|
if not key:
|
||||||
|
return False, "no API key"
|
||||||
|
code, out, err = run(
|
||||||
|
f'curl -s -o /dev/null -w "%{{http_code}}" -H "x-api-key: {key}" '
|
||||||
|
f'-H "x-api-provider: kimi-coding" '
|
||||||
|
f'https://api.kimi.com/coding/v1/models -X POST '
|
||||||
|
f'-H "content-type: application/json" '
|
||||||
|
f'-d \'{{"model":"kimi-k2.5","max_tokens":1,"messages":[{{"role":"user","content":"ping"}}]}}\' ',
|
||||||
|
timeout=15
|
||||||
|
)
|
||||||
|
if code == 0 and out in ("200", "429"):
|
||||||
|
return True, f"HTTP {out}"
|
||||||
|
return False, f"HTTP {out} err={err[:80]}"
|
||||||
|
|
||||||
|
def check_local_llama():
|
||||||
|
"""Is local llama.cpp serving?"""
|
||||||
|
code, out, err = run("curl -s http://localhost:8081/v1/models", timeout=5)
|
||||||
|
if code == 0 and "hermes" in out.lower():
|
||||||
|
return True, "serving"
|
||||||
|
return False, f"exit={code}"
|
||||||
|
|
||||||
|
def check_ollama():
|
||||||
|
"""Is Ollama running?"""
|
||||||
|
code, out, err = run("curl -s http://localhost:11434/api/tags", timeout=5)
|
||||||
|
if code == 0 and "models" in out:
|
||||||
|
return True, "running"
|
||||||
|
return False, f"exit={code}"
|
||||||
|
|
||||||
|
def check_gitea():
|
||||||
|
"""Can we reach the Forge?"""
|
||||||
|
token_path = Path.home() / ".config" / "gitea" / "timmy-token"
|
||||||
|
if not token_path.exists():
|
||||||
|
return False, "no token"
|
||||||
|
token = token_path.read_text().strip()
|
||||||
|
code, out, err = run(
|
||||||
|
f'curl -s -o /dev/null -w "%{{http_code}}" -H "Authorization: token {token}" '
|
||||||
|
f'"{FORGE_URL}/api/v1/user"',
|
||||||
|
timeout=10
|
||||||
|
)
|
||||||
|
if code == 0 and out == "200":
|
||||||
|
return True, "reachable"
|
||||||
|
return False, f"HTTP {out}"
|
||||||
|
|
||||||
|
def check_vps(ip, name):
|
||||||
|
"""Can we SSH into a VPS?"""
|
||||||
|
code, out, err = run(f"ssh -o ConnectTimeout=5 root@{ip} 'echo alive'", timeout=10)
|
||||||
|
if code == 0 and "alive" in out:
|
||||||
|
return True, "alive"
|
||||||
|
return False, f"unreachable"
|
||||||
|
|
||||||
|
# ─── FALLBACK ACTIONS ───
|
||||||
|
|
||||||
|
def fallback_to_local_model(cfg):
|
||||||
|
"""Switch primary model from Kimi to local llama.cpp"""
|
||||||
|
if not BACKUP_CONFIG.exists():
|
||||||
|
shutil.copy2(CONFIG_PATH, BACKUP_CONFIG)
|
||||||
|
|
||||||
|
cfg["model"]["provider"] = "local-llama.cpp"
|
||||||
|
cfg["model"]["default"] = "hermes3"
|
||||||
|
save_config(cfg)
|
||||||
|
return "Switched primary model to local-llama.cpp/hermes3"
|
||||||
|
|
||||||
|
def fallback_to_ollama(cfg):
|
||||||
|
"""Switch to Ollama if llama.cpp is also down"""
|
||||||
|
if not BACKUP_CONFIG.exists():
|
||||||
|
shutil.copy2(CONFIG_PATH, BACKUP_CONFIG)
|
||||||
|
|
||||||
|
cfg["model"]["provider"] = "ollama"
|
||||||
|
cfg["model"]["default"] = "gemma4:latest"
|
||||||
|
save_config(cfg)
|
||||||
|
return "Switched primary model to ollama/gemma4:latest"
|
||||||
|
|
||||||
|
def enter_safe_mode(state):
|
||||||
|
"""Pause all non-essential cron jobs, alert Alexander"""
|
||||||
|
state["safe_mode"] = True
|
||||||
|
state["safe_mode_entered"] = datetime.now().isoformat()
|
||||||
|
save_state(state)
|
||||||
|
return "SAFE MODE: All inference down. Cron jobs should be paused. Alert Alexander."
|
||||||
|
|
||||||
|
def restore_config():
|
||||||
|
"""Restore pre-fallback config when primary recovers"""
|
||||||
|
if BACKUP_CONFIG.exists():
|
||||||
|
shutil.copy2(BACKUP_CONFIG, CONFIG_PATH)
|
||||||
|
BACKUP_CONFIG.unlink()
|
||||||
|
return "Restored original config from backup"
|
||||||
|
return "No backup config to restore"
|
||||||
|
|
||||||
|
# ─── MAIN DIAGNOSIS AND FALLBACK ENGINE ───
|
||||||
|
|
||||||
|
def diagnose_and_fallback():
|
||||||
|
state = load_state()
|
||||||
|
cfg = load_config()
|
||||||
|
|
||||||
|
results = {
|
||||||
|
"timestamp": datetime.now().isoformat(),
|
||||||
|
"checks": {},
|
||||||
|
"actions": [],
|
||||||
|
"status": "healthy"
|
||||||
|
}
|
||||||
|
|
||||||
|
# Check all systems
|
||||||
|
kimi_ok, kimi_msg = check_kimi()
|
||||||
|
results["checks"]["kimi-coding"] = {"ok": kimi_ok, "msg": kimi_msg}
|
||||||
|
|
||||||
|
llama_ok, llama_msg = check_local_llama()
|
||||||
|
results["checks"]["local_llama"] = {"ok": llama_ok, "msg": llama_msg}
|
||||||
|
|
||||||
|
ollama_ok, ollama_msg = check_ollama()
|
||||||
|
results["checks"]["ollama"] = {"ok": ollama_ok, "msg": ollama_msg}
|
||||||
|
|
||||||
|
gitea_ok, gitea_msg = check_gitea()
|
||||||
|
results["checks"]["gitea"] = {"ok": gitea_ok, "msg": gitea_msg}
|
||||||
|
|
||||||
|
# VPS checks
|
||||||
|
vpses = [
|
||||||
|
("167.99.126.228", "Allegro"),
|
||||||
|
("143.198.27.163", "Ezra"),
|
||||||
|
("159.203.146.185", "Bezalel"),
|
||||||
|
]
|
||||||
|
for ip, name in vpses:
|
||||||
|
vps_ok, vps_msg = check_vps(ip, name)
|
||||||
|
results["checks"][f"vps_{name.lower()}"] = {"ok": vps_ok, "msg": vps_msg}
|
||||||
|
|
||||||
|
current_provider = cfg.get("model", {}).get("provider", "kimi-coding")
|
||||||
|
|
||||||
|
# ─── FALLBACK LOGIC ───
|
||||||
|
|
||||||
|
# Case 1: Primary (Kimi) down, local available
|
||||||
|
if not kimi_ok and current_provider == "kimi-coding":
|
||||||
|
if llama_ok:
|
||||||
|
msg = fallback_to_local_model(cfg)
|
||||||
|
results["actions"].append(msg)
|
||||||
|
state["active_fallbacks"].append("kimi->local-llama")
|
||||||
|
results["status"] = "degraded_local"
|
||||||
|
elif ollama_ok:
|
||||||
|
msg = fallback_to_ollama(cfg)
|
||||||
|
results["actions"].append(msg)
|
||||||
|
state["active_fallbacks"].append("kimi->ollama")
|
||||||
|
results["status"] = "degraded_ollama"
|
||||||
|
else:
|
||||||
|
msg = enter_safe_mode(state)
|
||||||
|
results["actions"].append(msg)
|
||||||
|
results["status"] = "safe_mode"
|
||||||
|
|
||||||
|
# Case 2: Already on fallback, check if primary recovered
|
||||||
|
elif kimi_ok and "kimi->local-llama" in state.get("active_fallbacks", []):
|
||||||
|
msg = restore_config()
|
||||||
|
results["actions"].append(msg)
|
||||||
|
state["active_fallbacks"].remove("kimi->local-llama")
|
||||||
|
results["status"] = "recovered"
|
||||||
|
elif kimi_ok and "kimi->ollama" in state.get("active_fallbacks", []):
|
||||||
|
msg = restore_config()
|
||||||
|
results["actions"].append(msg)
|
||||||
|
state["active_fallbacks"].remove("kimi->ollama")
|
||||||
|
results["status"] = "recovered"
|
||||||
|
|
||||||
|
# Case 3: Gitea down — just flag it, work locally
|
||||||
|
if not gitea_ok:
|
||||||
|
results["actions"].append("WARN: Gitea unreachable — work cached locally until recovery")
|
||||||
|
if "gitea_down" not in state.get("active_fallbacks", []):
|
||||||
|
state["active_fallbacks"].append("gitea_down")
|
||||||
|
results["status"] = max(results["status"], "degraded_gitea", key=lambda x: ["healthy", "recovered", "degraded_gitea", "degraded_local", "degraded_ollama", "safe_mode"].index(x) if x in ["healthy", "recovered", "degraded_gitea", "degraded_local", "degraded_ollama", "safe_mode"] else 0)
|
||||||
|
elif "gitea_down" in state.get("active_fallbacks", []):
|
||||||
|
state["active_fallbacks"].remove("gitea_down")
|
||||||
|
results["actions"].append("Gitea recovered — resume normal operations")
|
||||||
|
|
||||||
|
# Case 4: VPS agents down
|
||||||
|
for ip, name in vpses:
|
||||||
|
key = f"vps_{name.lower()}"
|
||||||
|
if not results["checks"][key]["ok"]:
|
||||||
|
results["actions"].append(f"ALERT: {name} VPS ({ip}) unreachable — lazarus protocol needed")
|
||||||
|
|
||||||
|
save_state(state)
|
||||||
|
return results
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
results = diagnose_and_fallback()
|
||||||
|
print(json.dumps(results, indent=2))
|
||||||
|
|
||||||
|
# Exit codes for cron integration
|
||||||
|
if results["status"] == "safe_mode":
|
||||||
|
sys.exit(2)
|
||||||
|
elif results["status"].startswith("degraded"):
|
||||||
|
sys.exit(1)
|
||||||
|
else:
|
||||||
|
sys.exit(0)
|
||||||
@@ -19,25 +19,25 @@ PASS=0
|
|||||||
FAIL=0
|
FAIL=0
|
||||||
WARN=0
|
WARN=0
|
||||||
|
|
||||||
check_anthropic_model() {
|
check_kimi_model() {
|
||||||
local model="$1"
|
local model="$1"
|
||||||
local label="$2"
|
local label="$2"
|
||||||
local api_key="${ANTHROPIC_API_KEY:-}"
|
local api_key="${KIMI_API_KEY:-}"
|
||||||
|
|
||||||
if [ -z "$api_key" ]; then
|
if [ -z "$api_key" ]; then
|
||||||
# Try loading from .env
|
# Try loading from .env
|
||||||
api_key=$(grep '^ANTHROPIC_API_KEY=' "${HERMES_HOME:-$HOME/.hermes}/.env" 2>/dev/null | head -1 | cut -d= -f2- | tr -d "'\"" || echo "")
|
api_key=$(grep '^KIMI_API_KEY=' "${HERMES_HOME:-$HOME/.hermes}/.env" 2>/dev/null | head -1 | cut -d= -f2- | tr -d "'\"" || echo "")
|
||||||
fi
|
fi
|
||||||
|
|
||||||
if [ -z "$api_key" ]; then
|
if [ -z "$api_key" ]; then
|
||||||
log "SKIP [$label] $model -- no ANTHROPIC_API_KEY"
|
log "SKIP [$label] $model -- no KIMI_API_KEY"
|
||||||
return 0
|
return 0
|
||||||
fi
|
fi
|
||||||
|
|
||||||
response=$(curl -sf --max-time 10 -X POST \
|
response=$(curl -sf --max-time 10 -X POST \
|
||||||
"https://api.anthropic.com/v1/messages" \
|
"https://api.kimi.com/coding/v1/chat/completions" \
|
||||||
-H "x-api-key: ${api_key}" \
|
-H "x-api-key: ${api_key}" \
|
||||||
-H "anthropic-version: 2023-06-01" \
|
-H "x-api-provider: kimi-coding" \
|
||||||
-H "content-type: application/json" \
|
-H "content-type: application/json" \
|
||||||
-d "{\"model\":\"${model}\",\"max_tokens\":1,\"messages\":[{\"role\":\"user\",\"content\":\"hi\"}]}" 2>&1 || echo "ERROR")
|
-d "{\"model\":\"${model}\",\"max_tokens\":1,\"messages\":[{\"role\":\"user\",\"content\":\"hi\"}]}" 2>&1 || echo "ERROR")
|
||||||
|
|
||||||
@@ -85,26 +85,26 @@ else:
|
|||||||
print('')
|
print('')
|
||||||
" 2>/dev/null || echo "")
|
" 2>/dev/null || echo "")
|
||||||
|
|
||||||
if [ -n "$primary" ] && [ "$provider" = "anthropic" ]; then
|
if [ -n "$primary" ] && [ "$provider" = "kimi-coding" ]; then
|
||||||
if check_anthropic_model "$primary" "PRIMARY"; then
|
if check_kimi_model "$primary" "PRIMARY"; then
|
||||||
PASS=$((PASS + 1))
|
PASS=$((PASS + 1))
|
||||||
else
|
else
|
||||||
rc=$?
|
rc=$?
|
||||||
if [ "$rc" -eq 1 ]; then
|
if [ "$rc" -eq 1 ]; then
|
||||||
FAIL=$((FAIL + 1))
|
FAIL=$((FAIL + 1))
|
||||||
log "CRITICAL: Primary model $primary is DEAD. Loops will fail."
|
log "CRITICAL: Primary model $primary is DEAD. Loops will fail."
|
||||||
log "Known good alternatives: claude-opus-4.6, claude-haiku-4-5-20251001"
|
log "Known good alternatives: kimi-k2.5, google/gemini-2.5-pro"
|
||||||
else
|
else
|
||||||
WARN=$((WARN + 1))
|
WARN=$((WARN + 1))
|
||||||
fi
|
fi
|
||||||
fi
|
fi
|
||||||
elif [ -n "$primary" ]; then
|
elif [ -n "$primary" ]; then
|
||||||
log "SKIP [PRIMARY] $primary -- non-anthropic provider ($provider), no validator yet"
|
log "SKIP [PRIMARY] $primary -- non-kimi provider ($provider), no validator yet"
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# Cron model check (haiku)
|
# Cron model check (haiku)
|
||||||
CRON_MODEL="claude-haiku-4-5-20251001"
|
CRON_MODEL="kimi-k2.5"
|
||||||
if check_anthropic_model "$CRON_MODEL" "CRON"; then
|
if check_kimi_model "$CRON_MODEL" "CRON"; then
|
||||||
PASS=$((PASS + 1))
|
PASS=$((PASS + 1))
|
||||||
else
|
else
|
||||||
rc=$?
|
rc=$?
|
||||||
|
|||||||
@@ -3,7 +3,7 @@
|
|||||||
# Uses Hermes CLI plus workforce-manager to triage and review.
|
# Uses Hermes CLI plus workforce-manager to triage and review.
|
||||||
# Timmy is the brain. Other agents are the hands.
|
# Timmy is the brain. Other agents are the hands.
|
||||||
|
|
||||||
set -uo pipefail
|
set -uo pipefail\n\nSCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
|
||||||
LOG_DIR="$HOME/.hermes/logs"
|
LOG_DIR="$HOME/.hermes/logs"
|
||||||
LOG="$LOG_DIR/timmy-orchestrator.log"
|
LOG="$LOG_DIR/timmy-orchestrator.log"
|
||||||
@@ -40,6 +40,7 @@ gather_state() {
|
|||||||
> "$state_dir/unassigned.txt"
|
> "$state_dir/unassigned.txt"
|
||||||
> "$state_dir/open_prs.txt"
|
> "$state_dir/open_prs.txt"
|
||||||
> "$state_dir/agent_status.txt"
|
> "$state_dir/agent_status.txt"
|
||||||
|
> "$state_dir/uncommitted_work.txt"
|
||||||
|
|
||||||
for repo in $REPOS; do
|
for repo in $REPOS; do
|
||||||
local short=$(echo "$repo" | cut -d/ -f2)
|
local short=$(echo "$repo" | cut -d/ -f2)
|
||||||
@@ -71,6 +72,24 @@ for p in json.load(sys.stdin):
|
|||||||
tail -50 "/tmp/kimi-heartbeat.log" 2>/dev/null | grep -c "FAILED:" | xargs -I{} echo "Kimi recent failures: {}" >> "$state_dir/agent_status.txt"
|
tail -50 "/tmp/kimi-heartbeat.log" 2>/dev/null | grep -c "FAILED:" | xargs -I{} echo "Kimi recent failures: {}" >> "$state_dir/agent_status.txt"
|
||||||
tail -1 "/tmp/kimi-heartbeat.log" 2>/dev/null | xargs -I{} echo "Kimi last event: {}" >> "$state_dir/agent_status.txt"
|
tail -1 "/tmp/kimi-heartbeat.log" 2>/dev/null | xargs -I{} echo "Kimi last event: {}" >> "$state_dir/agent_status.txt"
|
||||||
|
|
||||||
|
# Scan worktrees for uncommitted work
|
||||||
|
for wt_dir in "$HOME/worktrees"/*/; do
|
||||||
|
[ -d "$wt_dir" ] || continue
|
||||||
|
[ -d "$wt_dir/.git" ] || continue
|
||||||
|
local dirty
|
||||||
|
dirty=$(cd "$wt_dir" && git status --porcelain 2>/dev/null | wc -l | tr -d " ")
|
||||||
|
if [ "${dirty:-0}" -gt 0 ]; then
|
||||||
|
local branch
|
||||||
|
branch=$(cd "$wt_dir" && git branch --show-current 2>/dev/null || echo "?")
|
||||||
|
local age=""
|
||||||
|
local last_commit
|
||||||
|
last_commit=$(cd "$wt_dir" && git log -1 --format=%ct 2>/dev/null || echo 0)
|
||||||
|
local now=$(date +%s)
|
||||||
|
local stale_mins=$(( (now - last_commit) / 60 ))
|
||||||
|
echo "DIR=$wt_dir BRANCH=$branch DIRTY=$dirty STALE=${stale_mins}m" >> "$state_dir/uncommitted_work.txt"
|
||||||
|
fi
|
||||||
|
done
|
||||||
|
|
||||||
echo "$state_dir"
|
echo "$state_dir"
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -81,6 +100,25 @@ run_triage() {
|
|||||||
|
|
||||||
log "Cycle: $unassigned_count unassigned, $pr_count open PRs"
|
log "Cycle: $unassigned_count unassigned, $pr_count open PRs"
|
||||||
|
|
||||||
|
# Check for uncommitted work — nag if stale
|
||||||
|
local uncommitted_count
|
||||||
|
uncommitted_count=$(wc -l < "$state_dir/uncommitted_work.txt" 2>/dev/null | tr -d " " || echo 0)
|
||||||
|
if [ "${uncommitted_count:-0}" -gt 0 ]; then
|
||||||
|
log "WARNING: $uncommitted_count worktree(s) with uncommitted work"
|
||||||
|
while IFS= read -r line; do
|
||||||
|
log " UNCOMMITTED: $line"
|
||||||
|
# Auto-commit stale work (>60 min without commit)
|
||||||
|
local stale=$(echo "$line" | sed 's/.*STALE=\([0-9]*\)m.*/\1/')
|
||||||
|
local wt_dir=$(echo "$line" | sed 's/.*DIR=\([^ ]*\) .*/\1/')
|
||||||
|
if [ "${stale:-0}" -gt 60 ]; then
|
||||||
|
log " AUTO-COMMITTING stale work in $wt_dir (${stale}m stale)"
|
||||||
|
(cd "$wt_dir" && git add -A && git commit -m "WIP: orchestrator auto-commit — ${stale}m stale work
|
||||||
|
|
||||||
|
Preserved by timmy-orchestrator to prevent loss." 2>/dev/null && git push 2>/dev/null) && log " COMMITTED: $wt_dir" || log " COMMIT FAILED: $wt_dir"
|
||||||
|
fi
|
||||||
|
done < "$state_dir/uncommitted_work.txt"
|
||||||
|
fi
|
||||||
|
|
||||||
# If nothing to do, skip the LLM call
|
# If nothing to do, skip the LLM call
|
||||||
if [ "$unassigned_count" -eq 0 ] && [ "$pr_count" -eq 0 ]; then
|
if [ "$unassigned_count" -eq 0 ] && [ "$pr_count" -eq 0 ]; then
|
||||||
log "Nothing to triage"
|
log "Nothing to triage"
|
||||||
@@ -198,6 +236,12 @@ FOOTER
|
|||||||
log "=== Timmy Orchestrator Started (PID $$) ==="
|
log "=== Timmy Orchestrator Started (PID $$) ==="
|
||||||
log "Cycle: ${CYCLE_INTERVAL}s | Auto-assign: ${AUTO_ASSIGN_UNASSIGNED} | Inference surface: Hermes CLI"
|
log "Cycle: ${CYCLE_INTERVAL}s | Auto-assign: ${AUTO_ASSIGN_UNASSIGNED} | Inference surface: Hermes CLI"
|
||||||
|
|
||||||
|
# Start auto-commit-guard daemon for work preservation
|
||||||
|
if ! pgrep -f "auto-commit-guard.sh" >/dev/null 2>&1; then
|
||||||
|
nohup bash "$SCRIPT_DIR/auto-commit-guard.sh" 120 >> "$LOG_DIR/auto-commit-guard.log" 2>&1 &
|
||||||
|
log "Started auto-commit-guard daemon (PID $!)"
|
||||||
|
fi
|
||||||
|
|
||||||
WORKFORCE_CYCLE=0
|
WORKFORCE_CYCLE=0
|
||||||
|
|
||||||
while true; do
|
while true; do
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
{
|
{
|
||||||
"updated_at": "2026-03-28T09:54:34.822062",
|
"updated_at": "2026-04-13T02:02:07.001824",
|
||||||
"platforms": {
|
"platforms": {
|
||||||
"discord": [
|
"discord": [
|
||||||
{
|
{
|
||||||
@@ -27,11 +27,81 @@
|
|||||||
"name": "Timmy Time",
|
"name": "Timmy Time",
|
||||||
"type": "group",
|
"type": "group",
|
||||||
"thread_id": null
|
"thread_id": null
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "-1003664764329:85",
|
||||||
|
"name": "Timmy Time / topic 85",
|
||||||
|
"type": "group",
|
||||||
|
"thread_id": "85"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "-1003664764329:111",
|
||||||
|
"name": "Timmy Time / topic 111",
|
||||||
|
"type": "group",
|
||||||
|
"thread_id": "111"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "-1003664764329:173",
|
||||||
|
"name": "Timmy Time / topic 173",
|
||||||
|
"type": "group",
|
||||||
|
"thread_id": "173"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "7635059073",
|
||||||
|
"name": "Trip T",
|
||||||
|
"type": "dm",
|
||||||
|
"thread_id": null
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "-1003664764329:244",
|
||||||
|
"name": "Timmy Time / topic 244",
|
||||||
|
"type": "group",
|
||||||
|
"thread_id": "244"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "-1003664764329:972",
|
||||||
|
"name": "Timmy Time / topic 972",
|
||||||
|
"type": "group",
|
||||||
|
"thread_id": "972"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "-1003664764329:931",
|
||||||
|
"name": "Timmy Time / topic 931",
|
||||||
|
"type": "group",
|
||||||
|
"thread_id": "931"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "-1003664764329:957",
|
||||||
|
"name": "Timmy Time / topic 957",
|
||||||
|
"type": "group",
|
||||||
|
"thread_id": "957"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "-1003664764329:1297",
|
||||||
|
"name": "Timmy Time / topic 1297",
|
||||||
|
"type": "group",
|
||||||
|
"thread_id": "1297"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "-1003664764329:1316",
|
||||||
|
"name": "Timmy Time / topic 1316",
|
||||||
|
"type": "group",
|
||||||
|
"thread_id": "1316"
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"whatsapp": [],
|
"whatsapp": [],
|
||||||
|
"slack": [],
|
||||||
"signal": [],
|
"signal": [],
|
||||||
|
"mattermost": [],
|
||||||
|
"matrix": [],
|
||||||
|
"homeassistant": [],
|
||||||
"email": [],
|
"email": [],
|
||||||
"sms": []
|
"sms": [],
|
||||||
|
"dingtalk": [],
|
||||||
|
"feishu": [],
|
||||||
|
"wecom": [],
|
||||||
|
"wecom_callback": [],
|
||||||
|
"weixin": [],
|
||||||
|
"bluebubbles": []
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -7,7 +7,7 @@ Purpose:
|
|||||||
|
|
||||||
## What it is
|
## What it is
|
||||||
|
|
||||||
Code Claw is a separate local runtime from Hermes/OpenClaw.
|
Code Claw is a separate local runtime from Hermes.
|
||||||
|
|
||||||
Current lane:
|
Current lane:
|
||||||
- runtime: local patched `~/code-claw`
|
- runtime: local patched `~/code-claw`
|
||||||
|
|||||||
218
config.yaml
218
config.yaml
@@ -1,31 +1,23 @@
|
|||||||
model:
|
model:
|
||||||
default: hermes4:14b
|
default: claude-opus-4-6
|
||||||
provider: custom
|
provider: anthropic
|
||||||
context_length: 65536
|
|
||||||
base_url: http://localhost:8081/v1
|
|
||||||
toolsets:
|
toolsets:
|
||||||
- all
|
- all
|
||||||
agent:
|
agent:
|
||||||
max_turns: 30
|
max_turns: 30
|
||||||
reasoning_effort: xhigh
|
reasoning_effort: medium
|
||||||
verbose: false
|
verbose: false
|
||||||
terminal:
|
terminal:
|
||||||
backend: local
|
backend: local
|
||||||
cwd: .
|
cwd: .
|
||||||
timeout: 180
|
timeout: 180
|
||||||
env_passthrough: []
|
|
||||||
docker_image: nikolaik/python-nodejs:python3.11-nodejs20
|
docker_image: nikolaik/python-nodejs:python3.11-nodejs20
|
||||||
docker_forward_env: []
|
docker_forward_env: []
|
||||||
singularity_image: docker://nikolaik/python-nodejs:python3.11-nodejs20
|
singularity_image: docker://nikolaik/python-nodejs:python3.11-nodejs20
|
||||||
modal_image: nikolaik/python-nodejs:python3.11-nodejs20
|
modal_image: nikolaik/python-nodejs:python3.11-nodejs20
|
||||||
daytona_image: nikolaik/python-nodejs:python3.11-nodejs20
|
daytona_image: nikolaik/python-nodejs:python3.11-nodejs20
|
||||||
container_cpu: 1
|
container_cpu: 1
|
||||||
container_embeddings:
|
container_memory: 5120
|
||||||
provider: ollama
|
|
||||||
model: nomic-embed-text
|
|
||||||
base_url: http://localhost:11434/v1
|
|
||||||
|
|
||||||
memory: 5120
|
|
||||||
container_disk: 51200
|
container_disk: 51200
|
||||||
container_persistent: true
|
container_persistent: true
|
||||||
docker_volumes: []
|
docker_volumes: []
|
||||||
@@ -33,89 +25,74 @@ memory: 5120
|
|||||||
persistent_shell: true
|
persistent_shell: true
|
||||||
browser:
|
browser:
|
||||||
inactivity_timeout: 120
|
inactivity_timeout: 120
|
||||||
command_timeout: 30
|
|
||||||
record_sessions: false
|
record_sessions: false
|
||||||
checkpoints:
|
checkpoints:
|
||||||
enabled: true
|
enabled: false
|
||||||
max_snapshots: 50
|
max_snapshots: 50
|
||||||
compression:
|
compression:
|
||||||
enabled: true
|
enabled: true
|
||||||
threshold: 0.5
|
threshold: 0.5
|
||||||
target_ratio: 0.2
|
summary_model: qwen3:30b
|
||||||
protect_last_n: 20
|
summary_provider: custom
|
||||||
summary_model: ''
|
summary_base_url: http://localhost:11434/v1
|
||||||
summary_provider: ''
|
|
||||||
summary_base_url: ''
|
|
||||||
synthesis_model:
|
|
||||||
provider: custom
|
|
||||||
model: llama3:70b
|
|
||||||
base_url: http://localhost:8081/v1
|
|
||||||
|
|
||||||
smart_model_routing:
|
smart_model_routing:
|
||||||
enabled: true
|
enabled: false
|
||||||
max_simple_chars: 400
|
max_simple_chars: 160
|
||||||
max_simple_words: 75
|
max_simple_words: 28
|
||||||
cheap_model:
|
cheap_model: {}
|
||||||
provider: 'ollama'
|
|
||||||
model: 'gemma2:2b'
|
|
||||||
base_url: 'http://localhost:11434/v1'
|
|
||||||
api_key: ''
|
|
||||||
auxiliary:
|
auxiliary:
|
||||||
vision:
|
vision:
|
||||||
provider: auto
|
provider: custom
|
||||||
model: ''
|
model: qwen3:30b
|
||||||
base_url: ''
|
base_url: 'http://localhost:11434/v1'
|
||||||
api_key: ''
|
api_key: 'ollama'
|
||||||
timeout: 30
|
|
||||||
web_extract:
|
web_extract:
|
||||||
provider: auto
|
provider: custom
|
||||||
model: ''
|
model: qwen3:30b
|
||||||
base_url: ''
|
base_url: 'http://localhost:11434/v1'
|
||||||
api_key: ''
|
api_key: 'ollama'
|
||||||
compression:
|
compression:
|
||||||
provider: auto
|
provider: custom
|
||||||
model: ''
|
model: qwen3:30b
|
||||||
base_url: ''
|
base_url: 'http://localhost:11434/v1'
|
||||||
api_key: ''
|
api_key: 'ollama'
|
||||||
session_search:
|
session_search:
|
||||||
provider: auto
|
provider: custom
|
||||||
model: ''
|
model: qwen3:30b
|
||||||
base_url: ''
|
base_url: 'http://localhost:11434/v1'
|
||||||
api_key: ''
|
api_key: 'ollama'
|
||||||
skills_hub:
|
skills_hub:
|
||||||
provider: auto
|
provider: custom
|
||||||
model: ''
|
model: qwen3:30b
|
||||||
base_url: ''
|
base_url: 'http://localhost:11434/v1'
|
||||||
api_key: ''
|
api_key: 'ollama'
|
||||||
approval:
|
approval:
|
||||||
provider: auto
|
provider: auto
|
||||||
model: ''
|
model: ''
|
||||||
base_url: ''
|
base_url: ''
|
||||||
api_key: ''
|
api_key: ''
|
||||||
mcp:
|
mcp:
|
||||||
provider: auto
|
provider: custom
|
||||||
model: ''
|
model: qwen3:30b
|
||||||
base_url: ''
|
base_url: 'http://localhost:11434/v1'
|
||||||
api_key: ''
|
api_key: 'ollama'
|
||||||
flush_memories:
|
flush_memories:
|
||||||
provider: auto
|
provider: custom
|
||||||
model: ''
|
model: qwen3:30b
|
||||||
base_url: ''
|
base_url: 'http://localhost:11434/v1'
|
||||||
api_key: ''
|
api_key: 'ollama'
|
||||||
display:
|
display:
|
||||||
compact: false
|
compact: false
|
||||||
personality: ''
|
personality: ''
|
||||||
resume_display: full
|
resume_display: full
|
||||||
busy_input_mode: interrupt
|
|
||||||
bell_on_complete: false
|
bell_on_complete: false
|
||||||
show_reasoning: false
|
show_reasoning: false
|
||||||
streaming: false
|
streaming: false
|
||||||
show_cost: false
|
show_cost: false
|
||||||
skin: timmy
|
skin: timmy
|
||||||
tool_progress_command: false
|
|
||||||
tool_progress: all
|
tool_progress: all
|
||||||
privacy:
|
privacy:
|
||||||
redact_pii: true
|
redact_pii: false
|
||||||
tts:
|
tts:
|
||||||
provider: edge
|
provider: edge
|
||||||
edge:
|
edge:
|
||||||
@@ -124,7 +101,7 @@ tts:
|
|||||||
voice_id: pNInz6obpgDQGcFmaJgB
|
voice_id: pNInz6obpgDQGcFmaJgB
|
||||||
model_id: eleven_multilingual_v2
|
model_id: eleven_multilingual_v2
|
||||||
openai:
|
openai:
|
||||||
model: '' # disabled — use edge TTS locally
|
model: gpt-4o-mini-tts
|
||||||
voice: alloy
|
voice: alloy
|
||||||
neutts:
|
neutts:
|
||||||
ref_audio: ''
|
ref_audio: ''
|
||||||
@@ -160,7 +137,6 @@ delegation:
|
|||||||
provider: ''
|
provider: ''
|
||||||
base_url: ''
|
base_url: ''
|
||||||
api_key: ''
|
api_key: ''
|
||||||
max_iterations: 50
|
|
||||||
prefill_messages_file: ''
|
prefill_messages_file: ''
|
||||||
honcho: {}
|
honcho: {}
|
||||||
timezone: ''
|
timezone: ''
|
||||||
@@ -174,16 +150,7 @@ approvals:
|
|||||||
command_allowlist: []
|
command_allowlist: []
|
||||||
quick_commands: {}
|
quick_commands: {}
|
||||||
personalities: {}
|
personalities: {}
|
||||||
mesh:
|
|
||||||
enabled: true
|
|
||||||
blackboard_provider: local
|
|
||||||
nostr_discovery: true
|
|
||||||
consensus_mode: competitive
|
|
||||||
|
|
||||||
security:
|
security:
|
||||||
sovereign_audit: true
|
|
||||||
no_phone_home: true
|
|
||||||
|
|
||||||
redact_secrets: true
|
redact_secrets: true
|
||||||
tirith_enabled: true
|
tirith_enabled: true
|
||||||
tirith_path: tirith
|
tirith_path: tirith
|
||||||
@@ -193,55 +160,66 @@ security:
|
|||||||
enabled: false
|
enabled: false
|
||||||
domains: []
|
domains: []
|
||||||
shared_files: []
|
shared_files: []
|
||||||
_config_version: 10
|
# Author whitelist for task router (Issue #132)
|
||||||
platforms:
|
# Only users in this list can submit tasks via Gitea issues
|
||||||
api_server:
|
# Empty list = deny all (secure by default)
|
||||||
enabled: true
|
# Set via env var TIMMY_AUTHOR_WHITELIST as comma-separated list
|
||||||
extra:
|
author_whitelist: []
|
||||||
host: 0.0.0.0
|
_config_version: 9
|
||||||
port: 8642
|
|
||||||
session_reset:
|
session_reset:
|
||||||
mode: none
|
mode: none
|
||||||
idle_minutes: 0
|
idle_minutes: 0
|
||||||
custom_providers:
|
custom_providers:
|
||||||
- name: Local llama.cpp
|
- name: Local Ollama
|
||||||
base_url: http://localhost:8081/v1
|
base_url: http://localhost:11434/v1
|
||||||
api_key: none
|
api_key: ollama
|
||||||
model: hermes4:14b
|
model: qwen3:30b
|
||||||
# ── Emergency cloud provider — not used by default or any cron job.
|
|
||||||
# Available for explicit override only: hermes --model gemini-2.5-pro
|
|
||||||
- name: Google Gemini (emergency only)
|
|
||||||
base_url: https://generativelanguage.googleapis.com/v1beta/openai
|
|
||||||
api_key_env: GEMINI_API_KEY
|
|
||||||
model: gemini-2.5-pro
|
|
||||||
system_prompt_suffix: "You are Timmy. Your soul is defined in SOUL.md \u2014 read\
|
system_prompt_suffix: "You are Timmy. Your soul is defined in SOUL.md \u2014 read\
|
||||||
\ it, live it.\nYou run locally on your owner's machine via llama.cpp. You never\
|
\ it, live it.\nYou run locally on your owner's machine via Ollama. You never phone\
|
||||||
\ phone home.\nYou speak plainly. You prefer short sentences. Brevity is a kindness.\n\
|
\ home.\nYou speak plainly. You prefer short sentences. Brevity is a kindness.\n\
|
||||||
When you don't know something, say so. Refusal over fabrication.\nSovereignty and\
|
Source distinction: Tag every factual claim inline. Default is [generated] — you\
|
||||||
\ service always.\n"
|
\ are pattern-matching from training data. Only use [retrieved] when you can name\
|
||||||
|
\ the specific tool call or document from THIS conversation that provided the fact.\
|
||||||
|
\ If no tool was called, every claim is [generated]. No exceptions.\n\
|
||||||
|
Refusal over fabrication: When you generate a specific claim — a date, a number,\
|
||||||
|
\ a price, a version, a URL, a current event — and you cannot name a source from\
|
||||||
|
\ this conversation, say 'I don't know' instead. Do not guess. Do not hedge with\
|
||||||
|
\ 'probably' or 'approximately' as a substitute for knowledge. If your only source\
|
||||||
|
\ is training data and the claim could be wrong or outdated, the honest answer is\
|
||||||
|
\ 'I don't know — I can look this up if you'd like.' Prefer a true 'I don't know'\
|
||||||
|
\ over a plausible fabrication.\nSovereignty and service always.\n"
|
||||||
skills:
|
skills:
|
||||||
creation_nudge_interval: 15
|
creation_nudge_interval: 15
|
||||||
DISCORD_HOME_CHANNEL: '1476292315814297772'
|
|
||||||
providers:
|
# ── Fallback Model ────────────────────────────────────────────────────
|
||||||
ollama:
|
# Automatic provider failover when primary is unavailable.
|
||||||
base_url: http://localhost:11434/v1
|
# Uncomment and configure to enable. Triggers on rate limits (429),
|
||||||
model: hermes3:latest
|
# overload (529), service errors (503), or connection failures.
|
||||||
mcp_servers:
|
#
|
||||||
morrowind:
|
# Supported providers:
|
||||||
command: python3
|
# openrouter (OPENROUTER_API_KEY) — routes to any model
|
||||||
args:
|
# openai-codex (OAuth — hermes login) — OpenAI Codex
|
||||||
- /Users/apayne/.timmy/morrowind/mcp_server.py
|
# nous (OAuth — hermes login) — Nous Portal
|
||||||
env: {}
|
# zai (ZAI_API_KEY) — Z.AI / GLM
|
||||||
timeout: 30
|
# kimi-coding (KIMI_API_KEY) — Kimi / Moonshot
|
||||||
crucible:
|
# minimax (MINIMAX_API_KEY) — MiniMax
|
||||||
command: /Users/apayne/.hermes/hermes-agent/venv/bin/python3
|
# minimax-cn (MINIMAX_CN_API_KEY) — MiniMax (China)
|
||||||
args:
|
#
|
||||||
- /Users/apayne/.hermes/bin/crucible_mcp_server.py
|
# For custom OpenAI-compatible endpoints, add base_url and api_key_env.
|
||||||
env: {}
|
#
|
||||||
timeout: 120
|
# fallback_model:
|
||||||
connect_timeout: 60
|
# provider: openrouter
|
||||||
fallback_model:
|
# model: anthropic/claude-sonnet-4
|
||||||
provider: ollama
|
#
|
||||||
model: hermes3:latest
|
# ── Smart Model Routing ────────────────────────────────────────────────
|
||||||
base_url: http://localhost:11434/v1
|
# Optional cheap-vs-strong routing for simple turns.
|
||||||
api_key: ''
|
# Keeps the primary model for complex work, but can route short/simple
|
||||||
|
# messages to a cheaper model across providers.
|
||||||
|
#
|
||||||
|
# smart_model_routing:
|
||||||
|
# enabled: true
|
||||||
|
# max_simple_chars: 160
|
||||||
|
# max_simple_words: 28
|
||||||
|
# cheap_model:
|
||||||
|
# provider: openrouter
|
||||||
|
# model: google/gemini-2.5-flash
|
||||||
|
|||||||
212
cron/jobs-backup-2026-04-10.json
Normal file
212
cron/jobs-backup-2026-04-10.json
Normal file
@@ -0,0 +1,212 @@
|
|||||||
|
[
|
||||||
|
{
|
||||||
|
"job_id": "9e0624269ba7",
|
||||||
|
"name": "Triage Heartbeat",
|
||||||
|
"schedule": "every 15m",
|
||||||
|
"state": "paused"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "e29eda4a8548",
|
||||||
|
"name": "PR Review Sweep",
|
||||||
|
"schedule": "every 30m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "a77a87392582",
|
||||||
|
"name": "Health Monitor",
|
||||||
|
"schedule": "every 5m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "5e9d952871bc",
|
||||||
|
"name": "Agent Status Check",
|
||||||
|
"schedule": "every 10m",
|
||||||
|
"state": "paused"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "36fb2f630a17",
|
||||||
|
"name": "Hermes Philosophy Loop",
|
||||||
|
"schedule": "every 1440m",
|
||||||
|
"state": "paused"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "b40a96a2f48c",
|
||||||
|
"name": "wolf-eval-cycle",
|
||||||
|
"schedule": "every 240m",
|
||||||
|
"state": "paused"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "4204e568b862",
|
||||||
|
"name": "Burn Mode \u2014 Timmy Orchestrator",
|
||||||
|
"schedule": "every 15m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "0944a976d034",
|
||||||
|
"name": "Burn Mode",
|
||||||
|
"schedule": "every 15m",
|
||||||
|
"state": "paused"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "62016b960fa0",
|
||||||
|
"name": "velocity-engine",
|
||||||
|
"schedule": "every 30m",
|
||||||
|
"state": "paused"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "e9d49eeff79c",
|
||||||
|
"name": "weekly-skill-extraction",
|
||||||
|
"schedule": "every 10080m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "75c74a5bb563",
|
||||||
|
"name": "tower-tick",
|
||||||
|
"schedule": "every 1m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "390a19054d4c",
|
||||||
|
"name": "Burn Deadman",
|
||||||
|
"schedule": "every 30m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "05e3c13498fa",
|
||||||
|
"name": "Morning Report \u2014 Burn Mode",
|
||||||
|
"schedule": "0 6 * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "64fe44b512b9",
|
||||||
|
"name": "evennia-morning-report",
|
||||||
|
"schedule": "0 9 * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "3896a7fd9747",
|
||||||
|
"name": "Gitea Priority Inbox",
|
||||||
|
"schedule": "every 3m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "f64c2709270a",
|
||||||
|
"name": "Config Drift Guard",
|
||||||
|
"schedule": "every 30m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "fc6a75b7102a",
|
||||||
|
"name": "Gitea Event Watcher",
|
||||||
|
"schedule": "every 2m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "12e59648fb06",
|
||||||
|
"name": "Burndown Night Watcher",
|
||||||
|
"schedule": "every 15m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "35d3ada9cf8f",
|
||||||
|
"name": "Mempalace Forge \u2014 Issue Analysis",
|
||||||
|
"schedule": "every 60m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "190b6fb8dc91",
|
||||||
|
"name": "Mempalace Watchtower \u2014 Fleet Health",
|
||||||
|
"schedule": "every 30m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "710ab589813c",
|
||||||
|
"name": "Ezra Health Monitor",
|
||||||
|
"schedule": "every 15m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "a0a9cce4575c",
|
||||||
|
"name": "daily-poka-yoke-ultraplan-awesometools",
|
||||||
|
"schedule": "every 1440m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "adc3a51457bd",
|
||||||
|
"name": "vps-agent-dispatch",
|
||||||
|
"schedule": "every 10m",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "afd2c4eac44d",
|
||||||
|
"name": "Project Mnemosyne Nightly Burn v2",
|
||||||
|
"schedule": "*/30 * * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "f3a3c2832af0",
|
||||||
|
"name": "gemma4-multimodal-worker",
|
||||||
|
"schedule": "once in 15m",
|
||||||
|
"state": "completed"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "c17a85c19838",
|
||||||
|
"name": "know-thy-father-analyzer",
|
||||||
|
"schedule": "0 * * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "2490fc01a14d",
|
||||||
|
"name": "Testament Burn - 10min work loop",
|
||||||
|
"schedule": "*/10 * * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "f5e858159d97",
|
||||||
|
"name": "Timmy Foundation Burn \u2014 15min PR loop",
|
||||||
|
"schedule": "*/15 * * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "5e262fb9bdce",
|
||||||
|
"name": "nightwatch-health-monitor",
|
||||||
|
"schedule": "*/15 * * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "f2b33a9dcf96",
|
||||||
|
"name": "nightwatch-mempalace-mine",
|
||||||
|
"schedule": "0 */2 * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "82cb9e76c54d",
|
||||||
|
"name": "nightwatch-backlog-burn",
|
||||||
|
"schedule": "0 */4 * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "d20e42a52863",
|
||||||
|
"name": "beacon-sprint",
|
||||||
|
"schedule": "*/15 * * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "579269489961",
|
||||||
|
"name": "testament-story",
|
||||||
|
"schedule": "*/15 * * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "2e5f9140d1ab",
|
||||||
|
"name": "nightwatch-research",
|
||||||
|
"schedule": "0 */2 * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"job_id": "aeba92fd65e6",
|
||||||
|
"name": "timmy-dreams",
|
||||||
|
"schedule": "30 5 * * *",
|
||||||
|
"state": "scheduled"
|
||||||
|
}
|
||||||
|
]
|
||||||
@@ -168,7 +168,35 @@
|
|||||||
"paused_reason": null,
|
"paused_reason": null,
|
||||||
"skills": [],
|
"skills": [],
|
||||||
"skill": null
|
"skill": null
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": "overnight-rd-nightly",
|
||||||
|
"name": "Overnight R&D Loop",
|
||||||
|
"prompt": "Run the overnight R&D automation: Deep Dive paper synthesis, tightening loop for tool-use training data, DPO export sweep, morning briefing prep. All local inference via Ollama.",
|
||||||
|
"schedule": {
|
||||||
|
"kind": "cron",
|
||||||
|
"expr": "0 2 * * *",
|
||||||
|
"display": "0 2 * * * (10 PM EDT)"
|
||||||
|
},
|
||||||
|
"schedule_display": "Nightly at 10 PM EDT",
|
||||||
|
"repeat": {
|
||||||
|
"times": null,
|
||||||
|
"completed": 0
|
||||||
|
},
|
||||||
|
"enabled": true,
|
||||||
|
"created_at": "2026-04-13T02:00:00+00:00",
|
||||||
|
"next_run_at": null,
|
||||||
|
"last_run_at": null,
|
||||||
|
"last_status": null,
|
||||||
|
"last_error": null,
|
||||||
|
"deliver": "local",
|
||||||
|
"origin": "perplexity/overnight-rd-automation",
|
||||||
|
"state": "scheduled",
|
||||||
|
"paused_at": null,
|
||||||
|
"paused_reason": null,
|
||||||
|
"skills": [],
|
||||||
|
"skill": null
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"updated_at": "2026-04-07T15:00:00+00:00"
|
"updated_at": "2026-04-13T02:00:00+00:00"
|
||||||
}
|
}
|
||||||
|
|||||||
14
cron/vps/allegro-crontab-backup.txt
Normal file
14
cron/vps/allegro-crontab-backup.txt
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
0 6 * * * /bin/bash /root/wizards/scripts/model_download_guard.sh >> /var/log/model_guard.log 2>&1
|
||||||
|
|
||||||
|
# Allegro Hybrid Heartbeat — quick wins every 15 min
|
||||||
|
*/15 * * * * /usr/bin/python3 /root/allegro/heartbeat_daemon.py >> /var/log/allegro_heartbeat.log 2>&1
|
||||||
|
|
||||||
|
# Allegro Burn Mode Cron Jobs - Deployed via issue #894
|
||||||
|
|
||||||
|
0 6 * * * cd /root/.hermes && python3 -c "import hermes_agent; from hermes_tools import terminal; output = terminal('echo \"Morning Report: $(date)\"'); print(output.get('output', ''))" >> /root/.hermes/logs/morning-report-$(date +\%Y\%m\%d).log 2>&1 # Allegro Morning Report at 0600
|
||||||
|
|
||||||
|
0,30 * * * * cd /root/.hermes && python3 /root/.hermes/retry_wrapper.py "python3 allegro/quick-lane-check.py" >> burn-logs/quick-lane-$(date +\%Y\%m\%d).log 2>&1 # Allegro Burn Loop #1 (with retry)
|
||||||
|
15,45 * * * * cd /root/.hermes && python3 /root/.hermes/retry_wrapper.py "python3 allegro/burn-mode-validator.py" >> burn-logs/validator-$(date +\%Y\%m\%d).log 2>&1 # Allegro Burn Loop #2 (with retry)
|
||||||
|
|
||||||
|
*/2 * * * * /root/wizards/bezalel/dead_man_monitor.sh
|
||||||
|
*/2 * * * * /root/wizards/allegro/bin/config-deadman.sh
|
||||||
10
cron/vps/bezalel-crontab-backup.txt
Normal file
10
cron/vps/bezalel-crontab-backup.txt
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
0 2 * * * /root/wizards/bezalel/run_nightly_watch.sh
|
||||||
|
0 3 * * * /root/wizards/bezalel/mempalace_nightly.sh
|
||||||
|
*/10 * * * * pgrep -f "act_runner daemon" > /dev/null || (cd /opt/gitea-runner && nohup ./act_runner daemon > /var/log/gitea-runner.log 2>&1 &)
|
||||||
|
30 3 * * * /root/wizards/bezalel/backup_databases.sh
|
||||||
|
*/15 * * * * /root/wizards/bezalel/meta_heartbeat.sh
|
||||||
|
0 4 * * * /root/wizards/bezalel/secret_guard.sh
|
||||||
|
0 4 * * * /usr/bin/env bash /root/timmy-home/scripts/backup_pipeline.sh >> /var/log/timmy/backup_pipeline_cron.log 2>&1
|
||||||
|
0 6 * * * /usr/bin/python3 /root/wizards/bezalel/ultraplan.py >> /var/log/bezalel-ultraplan.log 2>&1
|
||||||
|
@reboot /root/wizards/bezalel/emacs-daemon-start.sh
|
||||||
|
@reboot /root/wizards/bezalel/ngircd-start.sh
|
||||||
13
cron/vps/ezra-crontab-backup.txt
Normal file
13
cron/vps/ezra-crontab-backup.txt
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
# Burn Mode Cycles — 15 min autonomous loops
|
||||||
|
*/15 * * * * /root/wizards/ezra/bin/burn-mode.sh >> /root/wizards/ezra/reports/burn-cron.log 2>&1
|
||||||
|
|
||||||
|
# Household Snapshots — automated heartbeats and snapshots
|
||||||
|
# Ezra Self-Improvement Automation Suite
|
||||||
|
*/5 * * * * /usr/bin/python3 /root/wizards/ezra/tools/gitea_monitor.py >> /root/wizards/ezra/reports/gitea-monitor.log 2>&1
|
||||||
|
*/5 * * * * /usr/bin/python3 /root/wizards/ezra/tools/awareness_loop.py >> /root/wizards/ezra/reports/awareness-loop.log 2>&1
|
||||||
|
*/10 * * * * /usr/bin/python3 /root/wizards/ezra/tools/cron_health_monitor.py >> /root/wizards/ezra/reports/cron-health.log 2>&1
|
||||||
|
0 6 * * * /usr/bin/python3 /root/wizards/ezra/tools/morning_kt_compiler.py >> /root/wizards/ezra/reports/morning-kt.log 2>&1
|
||||||
|
5 6 * * * /usr/bin/python3 /root/wizards/ezra/tools/burndown_generator.py >> /root/wizards/ezra/reports/burndown.log 2>&1
|
||||||
|
0 3 * * * /root/wizards/ezra/mempalace_nightly.sh >> /var/log/ezra_mempalace_cron.log 2>&1
|
||||||
|
*/15 * * * * GITEA_TOKEN=6de6aa...1117 /root/wizards/ezra/dispatch-direct.sh >> /root/wizards/ezra/dispatch-cron.log 2>&1
|
||||||
|
|
||||||
24
deploy/auto-commit-guard.plist
Normal file
24
deploy/auto-commit-guard.plist
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
<?xml version="1.0" encoding="UTF-8"?>
|
||||||
|
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
|
||||||
|
<plist version="1.0">
|
||||||
|
<dict>
|
||||||
|
<key>Label</key>
|
||||||
|
<string>ai.timmy.auto-commit-guard</string>
|
||||||
|
<key>ProgramArguments</key>
|
||||||
|
<array>
|
||||||
|
<string>/bin/bash</string>
|
||||||
|
<string>/Users/apayne/.hermes/bin/auto-commit-guard.sh</string>
|
||||||
|
<string>120</string>
|
||||||
|
</array>
|
||||||
|
<key>RunAtLoad</key>
|
||||||
|
<true/>
|
||||||
|
<key>KeepAlive</key>
|
||||||
|
<true/>
|
||||||
|
<key>StandardOutPath</key>
|
||||||
|
<string>/Users/apayne/.hermes/logs/auto-commit-guard.stdout.log</string>
|
||||||
|
<key>StandardErrorPath</key>
|
||||||
|
<string>/Users/apayne/.hermes/logs/auto-commit-guard.stderr.log</string>
|
||||||
|
<key>WorkingDirectory</key>
|
||||||
|
<string>/Users/apayne</string>
|
||||||
|
</dict>
|
||||||
|
</plist>
|
||||||
110
docs/FLEET_BEHAVIOUR_HARDENING.md
Normal file
110
docs/FLEET_BEHAVIOUR_HARDENING.md
Normal file
@@ -0,0 +1,110 @@
|
|||||||
|
# Fleet Behaviour Hardening — Review & Action Plan
|
||||||
|
|
||||||
|
**Author:** @perplexity
|
||||||
|
**Date:** 2026-04-08
|
||||||
|
**Context:** Alexander asked: "Is it the memory system or the behaviour guardrails?"
|
||||||
|
**Answer:** It's the guardrails. The memory system is adequate. The enforcement machinery is aspirational.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Diagnosis: Why the Fleet Isn't Smart Enough
|
||||||
|
|
||||||
|
After auditing SOUL.md, config.yaml, all 8 playbooks, the orchestrator, the guard scripts, and the v7.0.0 checkin, the pattern is clear:
|
||||||
|
|
||||||
|
**The fleet has excellent design documents and broken enforcement.**
|
||||||
|
|
||||||
|
| Layer | Design Quality | Enforcement Quality | Gap |
|
||||||
|
|---|---|---|---|
|
||||||
|
| SOUL.md | Excellent | None — no code reads it at runtime | Philosophy without machinery |
|
||||||
|
| Playbooks (7 yaml) | Good lane map | Not invoked by orchestrator | Playbooks exist but nobody calls them |
|
||||||
|
| Guard scripts (9) | Solid code | 1 of 9 wired (#395 audit) | 89% of guards are dead code |
|
||||||
|
| Orchestrator | Sound design | Gateway dispatch is a no-op (#391) | Assigns issues but doesn't trigger work |
|
||||||
|
| Cycle Guard | Good 10-min rule | No cron/loop calls it | Discipline without enforcement |
|
||||||
|
| PR Reviewer | Clear rules | Runs every 30m (if scheduled) | Only guard that might actually fire |
|
||||||
|
| Memory (MemPalace) | Working code | Retrieval enforcer wired | Actually operational |
|
||||||
|
|
||||||
|
### The Core Problem
|
||||||
|
|
||||||
|
Agents pick up issues and produce output, but there is **no pre-task checklist** and **no post-task quality gate**. An agent can:
|
||||||
|
|
||||||
|
1. Start work without checking if someone else already did it
|
||||||
|
2. Produce output without running tests
|
||||||
|
3. Submit a PR without verifying it addresses the issue
|
||||||
|
4. Work for hours on something out of scope
|
||||||
|
5. Create duplicate branches/PRs without detection
|
||||||
|
|
||||||
|
The SOUL.md says "grounding before generation" but no code enforces it.
|
||||||
|
The playbooks define lanes but the orchestrator doesn't load them.
|
||||||
|
The guards exist but nothing calls them.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What the Fleet Needs (Priority Order)
|
||||||
|
|
||||||
|
### 1. Pre-Task Gate (MISSING — this PR adds it)
|
||||||
|
|
||||||
|
Before an agent starts any issue:
|
||||||
|
- [ ] Check if issue is already assigned to another agent
|
||||||
|
- [ ] Check if a branch already exists for this issue
|
||||||
|
- [ ] Check if a PR already exists for this issue
|
||||||
|
- [ ] Load relevant MemPalace context (retrieval enforcer)
|
||||||
|
- [ ] Verify the agent has the right lane for this work (playbook check)
|
||||||
|
|
||||||
|
### 2. Post-Task Gate (MISSING — this PR adds it)
|
||||||
|
|
||||||
|
Before an agent submits a PR:
|
||||||
|
- [ ] Verify the diff addresses the issue title/body
|
||||||
|
- [ ] Run syntax_guard.py on changed files
|
||||||
|
- [ ] Check for duplicate PRs targeting the same issue
|
||||||
|
- [ ] Verify branch name follows convention
|
||||||
|
- [ ] Run tests if they exist for changed files
|
||||||
|
|
||||||
|
### 3. Wire the Existing Guards (8 of 9 are dead code)
|
||||||
|
|
||||||
|
Per #395 audit:
|
||||||
|
- Pre-commit hooks: need symlink on every machine
|
||||||
|
- Cycle guard: need cron/loop integration
|
||||||
|
- Forge health check: need cron entry
|
||||||
|
- Smoke test + deploy validate: need deploy script integration
|
||||||
|
|
||||||
|
### 4. Orchestrator Dispatch Actually Works
|
||||||
|
|
||||||
|
Per #391 audit: the orchestrator scores and assigns but the gateway dispatch just writes to `/tmp/hermes-dispatch.log`. Nobody reads that file. The dispatch needs to either:
|
||||||
|
- Trigger `hermes` CLI on the target machine, or
|
||||||
|
- Post a webhook that the agent loop picks up
|
||||||
|
|
||||||
|
### 5. Agent Self-Assessment Loop
|
||||||
|
|
||||||
|
After completing work, agents should answer:
|
||||||
|
- Did I address the issue as stated?
|
||||||
|
- Did I stay in scope?
|
||||||
|
- Did I check the palace for prior work?
|
||||||
|
- Did I run verification?
|
||||||
|
|
||||||
|
This is what SOUL.md calls "the apparatus that gives these words teeth."
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What's Working (Don't Touch)
|
||||||
|
|
||||||
|
- **MemPalace sovereign_store.py** — SQLite + FTS5 + HRR, operational
|
||||||
|
- **Retrieval enforcer** — wired to SovereignStore as of 14 hours ago
|
||||||
|
- **Wake-up protocol** — palace-first boot sequence
|
||||||
|
- **PR reviewer playbook** — clear rules, well-scoped
|
||||||
|
- **Issue triager playbook** — comprehensive lane map with 11 agents
|
||||||
|
- **Cycle guard code** — solid 10-min slice discipline (just needs wiring)
|
||||||
|
- **Config drift guard** — active cron, working
|
||||||
|
- **Dead man switch** — active, working
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Recommendation
|
||||||
|
|
||||||
|
The memory system is not the bottleneck. The behaviour guardrails are. Specifically:
|
||||||
|
|
||||||
|
1. **Add `task_gate.py`** — pre-task and post-task quality gates that every agent loop calls
|
||||||
|
2. **Wire cycle_guard.py** — add start/complete calls to agent loop
|
||||||
|
3. **Wire pre-commit hooks** — deploy script should symlink on provision
|
||||||
|
4. **Fix orchestrator dispatch** — make it actually trigger work, not just log
|
||||||
|
|
||||||
|
This PR adds item 1. Items 2-4 need SSH access and are flagged for Timmy/Allegro.
|
||||||
@@ -3,7 +3,7 @@
|
|||||||
Purpose:
|
Purpose:
|
||||||
- stand up the third wizard house as a Kimi-backed coding worker
|
- stand up the third wizard house as a Kimi-backed coding worker
|
||||||
- keep Hermes as the durable harness
|
- keep Hermes as the durable harness
|
||||||
- treat OpenClaw as optional shell frontage, not the bones
|
- Hermes is the durable harness — no intermediary gateway layers
|
||||||
|
|
||||||
Local proof already achieved:
|
Local proof already achieved:
|
||||||
|
|
||||||
@@ -40,5 +40,5 @@ bin/deploy-allegro-house.sh root@167.99.126.228
|
|||||||
|
|
||||||
Important nuance:
|
Important nuance:
|
||||||
- the Hermes/Kimi lane is the proven path
|
- the Hermes/Kimi lane is the proven path
|
||||||
- direct embedded OpenClaw Kimi model routing was not yet reliable locally
|
- direct embedded Kimi model routing was not yet reliable locally
|
||||||
- so the remote deployment keeps the minimal, proven architecture: Hermes house first
|
- so the remote deployment keeps the minimal, proven architecture: Hermes house first
|
||||||
@@ -81,17 +81,6 @@ launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/ai.hermes.gateway.plist
|
|||||||
- Old-state risk:
|
- Old-state risk:
|
||||||
- same class as main gateway, but isolated to fenrir profile state
|
- same class as main gateway, but isolated to fenrir profile state
|
||||||
|
|
||||||
#### 3. ai.openclaw.gateway
|
|
||||||
- Plist: ~/Library/LaunchAgents/ai.openclaw.gateway.plist
|
|
||||||
- Command: `node .../openclaw/dist/index.js gateway --port 18789`
|
|
||||||
- Logs:
|
|
||||||
- `~/.openclaw/logs/gateway.log`
|
|
||||||
- `~/.openclaw/logs/gateway.err.log`
|
|
||||||
- KeepAlive: yes
|
|
||||||
- RunAtLoad: yes
|
|
||||||
- Old-state risk:
|
|
||||||
- long-lived gateway survives toolchain assumptions and keeps accepting work even if upstream routing changed
|
|
||||||
|
|
||||||
#### 4. ai.timmy.kimi-heartbeat
|
#### 4. ai.timmy.kimi-heartbeat
|
||||||
- Plist: ~/Library/LaunchAgents/ai.timmy.kimi-heartbeat.plist
|
- Plist: ~/Library/LaunchAgents/ai.timmy.kimi-heartbeat.plist
|
||||||
- Command: `/bin/bash ~/.timmy/uniwizard/kimi-heartbeat.sh`
|
- Command: `/bin/bash ~/.timmy/uniwizard/kimi-heartbeat.sh`
|
||||||
@@ -295,7 +284,7 @@ launchctl list | egrep 'timmy|kimi|claude|max|dashboard|matrix|gateway|huey'
|
|||||||
|
|
||||||
List Timmy/Hermes launch agent files:
|
List Timmy/Hermes launch agent files:
|
||||||
```bash
|
```bash
|
||||||
find ~/Library/LaunchAgents -maxdepth 1 -name '*.plist' | egrep 'timmy|hermes|openclaw|tower'
|
find ~/Library/LaunchAgents -maxdepth 1 -name '*.plist' | egrep 'timmy|hermes|tower'
|
||||||
```
|
```
|
||||||
|
|
||||||
List running loop scripts:
|
List running loop scripts:
|
||||||
@@ -316,7 +305,6 @@ launchctl bootout gui/$(id -u) ~/Library/LaunchAgents/ai.timmy.kimi-heartbeat.pl
|
|||||||
launchctl bootout gui/$(id -u) ~/Library/LaunchAgents/ai.timmy.claudemax-watchdog.plist || true
|
launchctl bootout gui/$(id -u) ~/Library/LaunchAgents/ai.timmy.claudemax-watchdog.plist || true
|
||||||
launchctl bootout gui/$(id -u) ~/Library/LaunchAgents/ai.hermes.gateway.plist || true
|
launchctl bootout gui/$(id -u) ~/Library/LaunchAgents/ai.hermes.gateway.plist || true
|
||||||
launchctl bootout gui/$(id -u) ~/Library/LaunchAgents/ai.hermes.gateway-fenrir.plist || true
|
launchctl bootout gui/$(id -u) ~/Library/LaunchAgents/ai.hermes.gateway-fenrir.plist || true
|
||||||
launchctl bootout gui/$(id -u) ~/Library/LaunchAgents/ai.openclaw.gateway.plist || true
|
|
||||||
```
|
```
|
||||||
|
|
||||||
2. Kill manual loops
|
2. Kill manual loops
|
||||||
|
|||||||
68
docs/overnight-rd.md
Normal file
68
docs/overnight-rd.md
Normal file
@@ -0,0 +1,68 @@
|
|||||||
|
# Overnight R&D Automation
|
||||||
|
|
||||||
|
**Schedule**: Nightly at 10 PM EDT (02:00 UTC)
|
||||||
|
**Duration**: ~2-4 hours (self-limiting, finishes before 6 AM morning report)
|
||||||
|
**Cost**: $0 — all local Ollama inference
|
||||||
|
|
||||||
|
## Phases
|
||||||
|
|
||||||
|
### Phase 1: Deep Dive Intelligence
|
||||||
|
Runs the `intelligence/deepdive/pipeline.py` from the-nexus:
|
||||||
|
- Aggregates arXiv CS.AI, CS.CL, CS.LG RSS feeds (last 24h)
|
||||||
|
- Fetches OpenAI, Anthropic, DeepMind blog updates
|
||||||
|
- Filters for relevance using sentence-transformers embeddings
|
||||||
|
- Synthesizes a briefing using local Gemma 4 12B
|
||||||
|
- Saves briefing to `~/briefings/`
|
||||||
|
|
||||||
|
### Phase 2: Tightening Loop
|
||||||
|
Exercises Timmy's local tool-use capability:
|
||||||
|
- 10 tasks × 3 cycles = 30 task attempts per night
|
||||||
|
- File reading, writing, searching against real workspace files
|
||||||
|
- Each result logged as JSONL for training data analysis
|
||||||
|
- Tests sovereignty compliance (SOUL.md alignment, banned provider detection)
|
||||||
|
|
||||||
|
### Phase 3: DPO Export
|
||||||
|
Sweeps overnight Hermes sessions for training pair extraction:
|
||||||
|
- Converts good conversation pairs into DPO training format
|
||||||
|
- Saves to `~/.timmy/training-data/dpo-pairs/`
|
||||||
|
|
||||||
|
### Phase 4: Morning Prep
|
||||||
|
Compiles overnight findings into `~/.timmy/overnight-rd/latest_summary.md`
|
||||||
|
for consumption by the 6 AM `good_morning_report` task.
|
||||||
|
|
||||||
|
## Approved Providers
|
||||||
|
|
||||||
|
| Slot | Provider | Model |
|
||||||
|
|------|----------|-------|
|
||||||
|
| Synthesis | Ollama | gemma4:12b |
|
||||||
|
| Tool tasks | Ollama | hermes4:14b |
|
||||||
|
| Fallback | Ollama | gemma4:12b |
|
||||||
|
|
||||||
|
Anthropic is permanently banned (BANNED_PROVIDERS.yml, 2026-04-09).
|
||||||
|
|
||||||
|
## Outputs
|
||||||
|
|
||||||
|
| Path | Content |
|
||||||
|
|------|---------|
|
||||||
|
| `~/.timmy/overnight-rd/{run_id}/rd_log.jsonl` | Full task log |
|
||||||
|
| `~/.timmy/overnight-rd/{run_id}/rd_summary.md` | Run summary |
|
||||||
|
| `~/.timmy/overnight-rd/latest_summary.md` | Latest summary (for morning report) |
|
||||||
|
| `~/briefings/briefing_*.json` | Deep Dive briefings |
|
||||||
|
|
||||||
|
## Monitoring
|
||||||
|
|
||||||
|
Check the Huey consumer log:
|
||||||
|
```bash
|
||||||
|
tail -f ~/.timmy/timmy-config/logs/huey.log | grep overnight
|
||||||
|
```
|
||||||
|
|
||||||
|
Check the latest run summary:
|
||||||
|
```bash
|
||||||
|
cat ~/.timmy/overnight-rd/latest_summary.md
|
||||||
|
```
|
||||||
|
|
||||||
|
## Dependencies
|
||||||
|
|
||||||
|
- Deep Dive pipeline installed: `cd the-nexus/intelligence/deepdive && make install`
|
||||||
|
- Ollama running with gemma4:12b and hermes4:14b models
|
||||||
|
- Huey consumer running: `huey_consumer.py tasks.huey -w 2 -k thread`
|
||||||
@@ -14,7 +14,7 @@ from crewai.tools import BaseTool
|
|||||||
|
|
||||||
OPENROUTER_API_KEY = os.getenv(
|
OPENROUTER_API_KEY = os.getenv(
|
||||||
"OPENROUTER_API_KEY",
|
"OPENROUTER_API_KEY",
|
||||||
"dsk-or-v1-f60c89db12040267458165cf192e815e339eb70548e4a0a461f5f0f69e6ef8b0",
|
os.environ.get("OPENROUTER_API_KEY", ""),
|
||||||
)
|
)
|
||||||
|
|
||||||
llm = LLM(
|
llm = LLM(
|
||||||
|
|||||||
@@ -2,135 +2,128 @@ schema_version: 1
|
|||||||
status: proposed
|
status: proposed
|
||||||
runtime_wiring: false
|
runtime_wiring: false
|
||||||
owner: timmy-config
|
owner: timmy-config
|
||||||
|
|
||||||
ownership:
|
ownership:
|
||||||
owns:
|
owns:
|
||||||
- routing doctrine for task classes
|
- routing doctrine for task classes
|
||||||
- sidecar-readable per-agent fallback portfolios
|
- sidecar-readable per-agent fallback portfolios
|
||||||
- degraded-mode capability floors
|
- degraded-mode capability floors
|
||||||
does_not_own:
|
does_not_own:
|
||||||
- live queue state outside Gitea truth
|
- live queue state outside Gitea truth
|
||||||
- launchd or loop process state
|
- launchd or loop process state
|
||||||
- ad hoc worktree history
|
- ad hoc worktree history
|
||||||
|
|
||||||
policy:
|
policy:
|
||||||
require_four_slots_for_critical_agents: true
|
require_four_slots_for_critical_agents: true
|
||||||
terminal_fallback_must_be_usable: true
|
terminal_fallback_must_be_usable: true
|
||||||
forbid_synchronized_fleet_degradation: true
|
forbid_synchronized_fleet_degradation: true
|
||||||
forbid_human_token_fallbacks: true
|
forbid_human_token_fallbacks: true
|
||||||
anti_correlation_rule: no two critical agents may share the same primary+fallback1 pair
|
anti_correlation_rule: no two critical agents may share the same primary+fallback1 pair
|
||||||
|
|
||||||
sensitive_control_surfaces:
|
sensitive_control_surfaces:
|
||||||
- SOUL.md
|
- SOUL.md
|
||||||
- config.yaml
|
- config.yaml
|
||||||
- deploy.sh
|
- deploy.sh
|
||||||
- tasks.py
|
- tasks.py
|
||||||
- playbooks/
|
- playbooks/
|
||||||
- cron/
|
- cron/
|
||||||
- memories/
|
- memories/
|
||||||
- skins/
|
- skins/
|
||||||
- training/
|
- training/
|
||||||
|
|
||||||
role_classes:
|
role_classes:
|
||||||
judgment:
|
judgment:
|
||||||
current_surfaces:
|
current_surfaces:
|
||||||
- playbooks/issue-triager.yaml
|
- playbooks/issue-triager.yaml
|
||||||
- playbooks/pr-reviewer.yaml
|
- playbooks/pr-reviewer.yaml
|
||||||
- playbooks/verified-logic.yaml
|
- playbooks/verified-logic.yaml
|
||||||
task_classes:
|
task_classes:
|
||||||
- issue-triage
|
- issue-triage
|
||||||
- queue-routing
|
- queue-routing
|
||||||
- pr-review
|
- pr-review
|
||||||
- proof-check
|
- proof-check
|
||||||
- governance-review
|
- governance-review
|
||||||
degraded_mode:
|
degraded_mode:
|
||||||
fallback2:
|
fallback2:
|
||||||
allowed:
|
allowed:
|
||||||
- classify backlog
|
- classify backlog
|
||||||
- summarize risk
|
- summarize risk
|
||||||
- produce draft routing plans
|
- produce draft routing plans
|
||||||
- leave bounded labels or comments with evidence
|
- leave bounded labels or comments with evidence
|
||||||
denied:
|
denied:
|
||||||
- merge pull requests
|
- merge pull requests
|
||||||
- close or rewrite governing issues or PRs
|
- close or rewrite governing issues or PRs
|
||||||
- mutate sensitive control surfaces
|
- mutate sensitive control surfaces
|
||||||
- bulk-reassign the fleet
|
- bulk-reassign the fleet
|
||||||
- silently change routing policy
|
- silently change routing policy
|
||||||
terminal:
|
terminal:
|
||||||
lane: report-and-route
|
lane: report-and-route
|
||||||
allowed:
|
allowed:
|
||||||
- classify backlog
|
- classify backlog
|
||||||
- summarize risk
|
- summarize risk
|
||||||
- produce draft routing artifacts
|
- produce draft routing artifacts
|
||||||
denied:
|
denied:
|
||||||
- merge pull requests
|
- merge pull requests
|
||||||
- bulk-reassign the fleet
|
- bulk-reassign the fleet
|
||||||
- mutate sensitive control surfaces
|
- mutate sensitive control surfaces
|
||||||
|
|
||||||
builder:
|
builder:
|
||||||
current_surfaces:
|
current_surfaces:
|
||||||
- playbooks/bug-fixer.yaml
|
- playbooks/bug-fixer.yaml
|
||||||
- playbooks/test-writer.yaml
|
- playbooks/test-writer.yaml
|
||||||
- playbooks/refactor-specialist.yaml
|
- playbooks/refactor-specialist.yaml
|
||||||
task_classes:
|
task_classes:
|
||||||
- bug-fix
|
- bug-fix
|
||||||
- test-writing
|
- test-writing
|
||||||
- refactor
|
- refactor
|
||||||
- bounded-docs-change
|
- bounded-docs-change
|
||||||
degraded_mode:
|
degraded_mode:
|
||||||
fallback2:
|
fallback2:
|
||||||
allowed:
|
allowed:
|
||||||
- reversible single-issue changes
|
- reversible single-issue changes
|
||||||
- narrow docs fixes
|
- narrow docs fixes
|
||||||
- test scaffolds and reproducers
|
- test scaffolds and reproducers
|
||||||
denied:
|
denied:
|
||||||
- cross-repo changes
|
- cross-repo changes
|
||||||
- sensitive control-surface edits
|
- sensitive control-surface edits
|
||||||
- merge or release actions
|
- merge or release actions
|
||||||
terminal:
|
terminal:
|
||||||
lane: narrow-patch
|
lane: narrow-patch
|
||||||
allowed:
|
allowed:
|
||||||
- single-issue small patch
|
- single-issue small patch
|
||||||
- reproducer test
|
- reproducer test
|
||||||
- docs-only repair
|
- docs-only repair
|
||||||
denied:
|
denied:
|
||||||
- sensitive control-surface edits
|
- sensitive control-surface edits
|
||||||
- multi-file architecture work
|
- multi-file architecture work
|
||||||
- irreversible actions
|
- irreversible actions
|
||||||
|
|
||||||
wolf_bulk:
|
wolf_bulk:
|
||||||
current_surfaces:
|
current_surfaces:
|
||||||
- docs/automation-inventory.md
|
- docs/automation-inventory.md
|
||||||
- FALSEWORK.md
|
- FALSEWORK.md
|
||||||
task_classes:
|
task_classes:
|
||||||
- docs-inventory
|
- docs-inventory
|
||||||
- log-summarization
|
- log-summarization
|
||||||
- queue-hygiene
|
- queue-hygiene
|
||||||
- repetitive-small-diff
|
- repetitive-small-diff
|
||||||
- research-sweep
|
- research-sweep
|
||||||
degraded_mode:
|
degraded_mode:
|
||||||
fallback2:
|
fallback2:
|
||||||
allowed:
|
allowed:
|
||||||
- gather evidence
|
- gather evidence
|
||||||
- refresh inventories
|
- refresh inventories
|
||||||
- summarize logs
|
- summarize logs
|
||||||
- propose labels or routes
|
- propose labels or routes
|
||||||
denied:
|
denied:
|
||||||
- multi-repo branch fanout
|
- multi-repo branch fanout
|
||||||
- mass agent assignment
|
- mass agent assignment
|
||||||
- sensitive control-surface edits
|
- sensitive control-surface edits
|
||||||
- irreversible queue mutation
|
- irreversible queue mutation
|
||||||
terminal:
|
terminal:
|
||||||
lane: gather-and-summarize
|
lane: gather-and-summarize
|
||||||
allowed:
|
allowed:
|
||||||
- inventory refresh
|
- inventory refresh
|
||||||
- evidence bundles
|
- evidence bundles
|
||||||
- summaries
|
- summaries
|
||||||
denied:
|
denied:
|
||||||
- multi-repo branch fanout
|
- multi-repo branch fanout
|
||||||
- mass agent assignment
|
- mass agent assignment
|
||||||
- sensitive control-surface edits
|
- sensitive control-surface edits
|
||||||
|
|
||||||
routing:
|
routing:
|
||||||
issue-triage: judgment
|
issue-triage: judgment
|
||||||
queue-routing: judgment
|
queue-routing: judgment
|
||||||
@@ -146,22 +139,20 @@ routing:
|
|||||||
queue-hygiene: wolf_bulk
|
queue-hygiene: wolf_bulk
|
||||||
repetitive-small-diff: wolf_bulk
|
repetitive-small-diff: wolf_bulk
|
||||||
research-sweep: wolf_bulk
|
research-sweep: wolf_bulk
|
||||||
|
|
||||||
promotion_rules:
|
promotion_rules:
|
||||||
- If a wolf/bulk task touches a sensitive control surface, promote it to judgment.
|
- If a wolf/bulk task touches a sensitive control surface, promote it to judgment.
|
||||||
- If a builder task expands beyond 5 files, architecture review, or multi-repo coordination, promote it to judgment.
|
- If a builder task expands beyond 5 files, architecture review, or multi-repo coordination, promote it to judgment.
|
||||||
- If a terminal lane cannot produce a usable artifact, the portfolio is invalid and must be redesigned before wiring.
|
- If a terminal lane cannot produce a usable artifact, the portfolio is invalid and must be redesigned before wiring.
|
||||||
|
|
||||||
agents:
|
agents:
|
||||||
triage-coordinator:
|
triage-coordinator:
|
||||||
role_class: judgment
|
role_class: judgment
|
||||||
critical: true
|
critical: true
|
||||||
current_playbooks:
|
current_playbooks:
|
||||||
- playbooks/issue-triager.yaml
|
- playbooks/issue-triager.yaml
|
||||||
portfolio:
|
portfolio:
|
||||||
primary:
|
primary:
|
||||||
provider: anthropic
|
provider: kimi-coding
|
||||||
model: claude-opus-4-6
|
model: kimi-k2.5
|
||||||
lane: full-judgment
|
lane: full-judgment
|
||||||
fallback1:
|
fallback1:
|
||||||
provider: openai-codex
|
provider: openai-codex
|
||||||
@@ -177,19 +168,18 @@ agents:
|
|||||||
lane: report-and-route
|
lane: report-and-route
|
||||||
local_capable: true
|
local_capable: true
|
||||||
usable_output:
|
usable_output:
|
||||||
- backlog classification
|
- backlog classification
|
||||||
- routing draft
|
- routing draft
|
||||||
- risk summary
|
- risk summary
|
||||||
|
|
||||||
pr-reviewer:
|
pr-reviewer:
|
||||||
role_class: judgment
|
role_class: judgment
|
||||||
critical: true
|
critical: true
|
||||||
current_playbooks:
|
current_playbooks:
|
||||||
- playbooks/pr-reviewer.yaml
|
- playbooks/pr-reviewer.yaml
|
||||||
portfolio:
|
portfolio:
|
||||||
primary:
|
primary:
|
||||||
provider: anthropic
|
provider: kimi-coding
|
||||||
model: claude-opus-4-6
|
model: kimi-k2.5
|
||||||
lane: full-review
|
lane: full-review
|
||||||
fallback1:
|
fallback1:
|
||||||
provider: gemini
|
provider: gemini
|
||||||
@@ -205,17 +195,16 @@ agents:
|
|||||||
lane: low-stakes-diff-summary
|
lane: low-stakes-diff-summary
|
||||||
local_capable: false
|
local_capable: false
|
||||||
usable_output:
|
usable_output:
|
||||||
- diff risk summary
|
- diff risk summary
|
||||||
- explicit uncertainty notes
|
- explicit uncertainty notes
|
||||||
- merge-block recommendation
|
- merge-block recommendation
|
||||||
|
|
||||||
builder-main:
|
builder-main:
|
||||||
role_class: builder
|
role_class: builder
|
||||||
critical: true
|
critical: true
|
||||||
current_playbooks:
|
current_playbooks:
|
||||||
- playbooks/bug-fixer.yaml
|
- playbooks/bug-fixer.yaml
|
||||||
- playbooks/test-writer.yaml
|
- playbooks/test-writer.yaml
|
||||||
- playbooks/refactor-specialist.yaml
|
- playbooks/refactor-specialist.yaml
|
||||||
portfolio:
|
portfolio:
|
||||||
primary:
|
primary:
|
||||||
provider: openai-codex
|
provider: openai-codex
|
||||||
@@ -236,15 +225,14 @@ agents:
|
|||||||
lane: narrow-patch
|
lane: narrow-patch
|
||||||
local_capable: true
|
local_capable: true
|
||||||
usable_output:
|
usable_output:
|
||||||
- small patch
|
- small patch
|
||||||
- reproducer test
|
- reproducer test
|
||||||
- docs repair
|
- docs repair
|
||||||
|
|
||||||
wolf-sweeper:
|
wolf-sweeper:
|
||||||
role_class: wolf_bulk
|
role_class: wolf_bulk
|
||||||
critical: true
|
critical: true
|
||||||
current_world_state:
|
current_world_state:
|
||||||
- docs/automation-inventory.md
|
- docs/automation-inventory.md
|
||||||
portfolio:
|
portfolio:
|
||||||
primary:
|
primary:
|
||||||
provider: gemini
|
provider: gemini
|
||||||
@@ -264,21 +252,20 @@ agents:
|
|||||||
lane: gather-and-summarize
|
lane: gather-and-summarize
|
||||||
local_capable: true
|
local_capable: true
|
||||||
usable_output:
|
usable_output:
|
||||||
- inventory refresh
|
- inventory refresh
|
||||||
- evidence bundle
|
- evidence bundle
|
||||||
- summary comment
|
- summary comment
|
||||||
|
|
||||||
cross_checks:
|
cross_checks:
|
||||||
unique_primary_fallback1_pairs:
|
unique_primary_fallback1_pairs:
|
||||||
triage-coordinator:
|
triage-coordinator:
|
||||||
- anthropic/claude-opus-4-6
|
- kimi-coding/kimi-k2.5
|
||||||
- openai-codex/codex
|
- openai-codex/codex
|
||||||
pr-reviewer:
|
pr-reviewer:
|
||||||
- anthropic/claude-opus-4-6
|
- kimi-coding/kimi-k2.5
|
||||||
- gemini/gemini-2.5-pro
|
- gemini/gemini-2.5-pro
|
||||||
builder-main:
|
builder-main:
|
||||||
- openai-codex/codex
|
- openai-codex/codex
|
||||||
- kimi-coding/kimi-k2.5
|
- kimi-coding/kimi-k2.5
|
||||||
wolf-sweeper:
|
wolf-sweeper:
|
||||||
- gemini/gemini-2.5-flash
|
- gemini/gemini-2.5-flash
|
||||||
- groq/llama-3.3-70b-versatile
|
- groq/llama-3.3-70b-versatile
|
||||||
|
|||||||
@@ -104,7 +104,6 @@ Three primary resources govern the fleet:
|
|||||||
| Hermes gateway | 500 MB | Primary gateway |
|
| Hermes gateway | 500 MB | Primary gateway |
|
||||||
| Hermes agents (x3) | ~560 MB total | Multiple sessions |
|
| Hermes agents (x3) | ~560 MB total | Multiple sessions |
|
||||||
| Ollama | ~20 MB base + model memory | Model loading varies |
|
| Ollama | ~20 MB base + model memory | Model loading varies |
|
||||||
| OpenClaw | 350 MB | Gateway process |
|
|
||||||
| Evennia (server+portal) | 56 MB | Game world |
|
| Evennia (server+portal) | 56 MB | Game world |
|
||||||
|
|
||||||
---
|
---
|
||||||
@@ -146,7 +145,6 @@ This means Phase 3+ capabilities (orchestration, load balancing, etc.) are acces
|
|||||||
| Gitea | 23/24 | 95.8% | GOOD |
|
| Gitea | 23/24 | 95.8% | GOOD |
|
||||||
| Hermes Gateway | 23/24 | 95.8% | GOOD |
|
| Hermes Gateway | 23/24 | 95.8% | GOOD |
|
||||||
| Ollama | 24/24 | 100.0% | GOOD |
|
| Ollama | 24/24 | 100.0% | GOOD |
|
||||||
| OpenClaw | 24/24 | 100.0% | GOOD |
|
|
||||||
| Evennia | 24/24 | 100.0% | GOOD |
|
| Evennia | 24/24 | 100.0% | GOOD |
|
||||||
| Hermes Agent | 21/24 | 87.5% | **CHECK** |
|
| Hermes Agent | 21/24 | 87.5% | **CHECK** |
|
||||||
|
|
||||||
|
|||||||
@@ -58,7 +58,6 @@ LOCAL_CHECKS = {
|
|||||||
"hermes-gateway": "pgrep -f 'hermes gateway' > /dev/null 2>/dev/null",
|
"hermes-gateway": "pgrep -f 'hermes gateway' > /dev/null 2>/dev/null",
|
||||||
"hermes-agent": "pgrep -f 'hermes agent\\|hermes session' > /dev/null 2>/dev/null",
|
"hermes-agent": "pgrep -f 'hermes agent\\|hermes session' > /dev/null 2>/dev/null",
|
||||||
"ollama": "pgrep -f 'ollama serve' > /dev/null 2>/dev/null",
|
"ollama": "pgrep -f 'ollama serve' > /dev/null 2>/dev/null",
|
||||||
"openclaw": "pgrep -f 'openclaw' > /dev/null 2>/dev/null",
|
|
||||||
"evennia": "pgrep -f 'evennia' > /dev/null 2>/dev/null",
|
"evennia": "pgrep -f 'evennia' > /dev/null 2>/dev/null",
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -111,7 +111,7 @@ def update_uptime(checks: dict):
|
|||||||
save(data)
|
save(data)
|
||||||
|
|
||||||
if new_milestones:
|
if new_milestones:
|
||||||
print(f" UPTIME MILESTONE: {','.join(str(m) + '%') for m in new_milestones}")
|
print(f" UPTIME MILESTONE: {','.join((str(m) + '%') for m in new_milestones)}")
|
||||||
print(f" Current uptime: {recent_ok:.1f}%")
|
print(f" Current uptime: {recent_ok:.1f}%")
|
||||||
|
|
||||||
return data["uptime"]
|
return data["uptime"]
|
||||||
|
|||||||
@@ -59,7 +59,6 @@
|
|||||||
| Hermes agent (s007) | 62032 | ~200MB | Session active since 10:20PM prev |
|
| Hermes agent (s007) | 62032 | ~200MB | Session active since 10:20PM prev |
|
||||||
| Hermes agent (s001) | 12072 | ~178MB | Session active since Sun 6PM |
|
| Hermes agent (s001) | 12072 | ~178MB | Session active since Sun 6PM |
|
||||||
| Ollama | 71466 | ~20MB | /opt/homebrew/opt/ollama/bin/ollama serve |
|
| Ollama | 71466 | ~20MB | /opt/homebrew/opt/ollama/bin/ollama serve |
|
||||||
| OpenClaw gateway | 85834 | ~350MB | Tue 12PM start |
|
|
||||||
| Crucible MCP (x4) | multiple | ~10-69MB each | MCP server instances |
|
| Crucible MCP (x4) | multiple | ~10-69MB each | MCP server instances |
|
||||||
| Evennia Server | 66433 | ~49MB | Sun 10PM start, port 4000 |
|
| Evennia Server | 66433 | ~49MB | Sun 10PM start, port 4000 |
|
||||||
| Evennia Portal | 66423 | ~7MB | Sun 10PM start, port 4001 |
|
| Evennia Portal | 66423 | ~7MB | Sun 10PM start, port 4001 |
|
||||||
|
|||||||
@@ -77,7 +77,7 @@ def check_core_deps() -> CheckResult:
|
|||||||
"""Verify that hermes core Python packages are importable."""
|
"""Verify that hermes core Python packages are importable."""
|
||||||
required = [
|
required = [
|
||||||
"openai",
|
"openai",
|
||||||
"anthropic",
|
"kimi-coding",
|
||||||
"dotenv",
|
"dotenv",
|
||||||
"yaml",
|
"yaml",
|
||||||
"rich",
|
"rich",
|
||||||
@@ -206,8 +206,8 @@ def check_env_vars() -> CheckResult:
|
|||||||
"""Check that at least one LLM provider key is configured."""
|
"""Check that at least one LLM provider key is configured."""
|
||||||
provider_keys = [
|
provider_keys = [
|
||||||
"OPENROUTER_API_KEY",
|
"OPENROUTER_API_KEY",
|
||||||
"ANTHROPIC_API_KEY",
|
"KIMI_API_KEY",
|
||||||
"ANTHROPIC_TOKEN",
|
# "ANTHROPIC_TOKEN", # BANNED
|
||||||
"OPENAI_API_KEY",
|
"OPENAI_API_KEY",
|
||||||
"GLM_API_KEY",
|
"GLM_API_KEY",
|
||||||
"KIMI_API_KEY",
|
"KIMI_API_KEY",
|
||||||
@@ -225,7 +225,7 @@ def check_env_vars() -> CheckResult:
|
|||||||
passed=False,
|
passed=False,
|
||||||
message="No LLM provider API key found",
|
message="No LLM provider API key found",
|
||||||
fix_hint=(
|
fix_hint=(
|
||||||
"Set at least one of: OPENROUTER_API_KEY, ANTHROPIC_API_KEY, OPENAI_API_KEY "
|
"Set at least one of: OPENROUTER_API_KEY, KIMI_API_KEY, OPENAI_API_KEY "
|
||||||
"in ~/.hermes/.env or your shell."
|
"in ~/.hermes/.env or your shell."
|
||||||
),
|
),
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -25,7 +25,7 @@ services:
|
|||||||
- "traefik.http.routers.matrix-client.tls.certresolver=letsencrypt"
|
- "traefik.http.routers.matrix-client.tls.certresolver=letsencrypt"
|
||||||
- "traefik.http.routers.matrix-client.entrypoints=websecure"
|
- "traefik.http.routers.matrix-client.entrypoints=websecure"
|
||||||
- "traefik.http.services.matrix-client.loadbalancer.server.port=6167"
|
- "traefik.http.services.matrix-client.loadbalancer.server.port=6167"
|
||||||
|
|
||||||
# Federation (TCP 8448) - direct or via Traefik TCP entrypoint
|
# Federation (TCP 8448) - direct or via Traefik TCP entrypoint
|
||||||
# Option A: Direct host port mapping
|
# Option A: Direct host port mapping
|
||||||
# Option B: Traefik TCP router (requires Traefik federation entrypoint)
|
# Option B: Traefik TCP router (requires Traefik federation entrypoint)
|
||||||
|
|||||||
@@ -4,8 +4,8 @@ description: >
|
|||||||
reproduces the bug, then fixes the code, then verifies.
|
reproduces the bug, then fixes the code, then verifies.
|
||||||
|
|
||||||
model:
|
model:
|
||||||
preferred: claude-opus-4-6
|
preferred: kimi-k2.5
|
||||||
fallback: claude-sonnet-4-20250514
|
fallback: google/gemini-2.5-pro
|
||||||
max_turns: 30
|
max_turns: 30
|
||||||
temperature: 0.2
|
temperature: 0.2
|
||||||
|
|
||||||
|
|||||||
166
playbooks/fleet-guardrails.yaml
Normal file
166
playbooks/fleet-guardrails.yaml
Normal file
@@ -0,0 +1,166 @@
|
|||||||
|
# fleet-guardrails.yaml
|
||||||
|
# =====================
|
||||||
|
# Enforceable behaviour boundaries for every agent in the Timmy fleet.
|
||||||
|
# Consumed by task_gate.py (pre/post checks) and the orchestrator's
|
||||||
|
# dispatch loop. Every rule here is testable — no aspirational prose.
|
||||||
|
#
|
||||||
|
# Ref: SOUL.md "grounding before generation", Five Wisdoms #345
|
||||||
|
|
||||||
|
name: fleet-guardrails
|
||||||
|
version: "1.0.0"
|
||||||
|
description: >
|
||||||
|
Behaviour constraints that apply to ALL agents regardless of role.
|
||||||
|
These are the non-negotiable rules that task_gate.py enforces
|
||||||
|
before an agent may pick up work and after it claims completion.
|
||||||
|
|
||||||
|
# ─── UNIVERSAL CONSTRAINTS ───────────────────────────────────────
|
||||||
|
|
||||||
|
constraints:
|
||||||
|
|
||||||
|
# 1. Lane discipline — agents must stay in their lane
|
||||||
|
lane_enforcement:
|
||||||
|
enabled: true
|
||||||
|
source: playbooks/agent-lanes.json
|
||||||
|
on_violation: block_and_notify
|
||||||
|
description: >
|
||||||
|
An agent may only pick up issues tagged for its lane.
|
||||||
|
Cross-lane work requires explicit Timmy approval via
|
||||||
|
issue comment containing 'LANE_OVERRIDE: <agent>'.
|
||||||
|
|
||||||
|
# 2. Branch hygiene — no orphan branches
|
||||||
|
branch_hygiene:
|
||||||
|
enabled: true
|
||||||
|
max_branches_per_agent: 3
|
||||||
|
stale_branch_days: 7
|
||||||
|
naming_pattern: "{agent}/{issue_number}-{slug}"
|
||||||
|
on_violation: warn_then_block
|
||||||
|
description: >
|
||||||
|
Agents must follow branch naming conventions and clean up
|
||||||
|
after merge. No agent may have more than 3 active branches.
|
||||||
|
|
||||||
|
# 3. Issue ownership — no silent takeovers
|
||||||
|
issue_ownership:
|
||||||
|
enabled: true
|
||||||
|
require_assignment_before_work: true
|
||||||
|
max_concurrent_issues: 2
|
||||||
|
on_violation: block_and_notify
|
||||||
|
description: >
|
||||||
|
An agent must be assigned to an issue before creating a
|
||||||
|
branch or PR. No agent may work on more than 2 issues
|
||||||
|
simultaneously to prevent context-switching waste.
|
||||||
|
|
||||||
|
# 4. PR quality — minimum bar before review
|
||||||
|
pr_quality:
|
||||||
|
enabled: true
|
||||||
|
require_linked_issue: true
|
||||||
|
require_passing_ci: true
|
||||||
|
max_files_changed: 30
|
||||||
|
max_diff_lines: 2000
|
||||||
|
require_description: true
|
||||||
|
min_description_length: 50
|
||||||
|
on_violation: block_merge
|
||||||
|
description: >
|
||||||
|
Every PR must link an issue, pass CI, have a meaningful
|
||||||
|
description, and stay within scope. Giant PRs get rejected.
|
||||||
|
|
||||||
|
# 5. Grounding before generation — SOUL.md compliance
|
||||||
|
grounding:
|
||||||
|
enabled: true
|
||||||
|
require_issue_read_before_branch: true
|
||||||
|
require_existing_code_review: true
|
||||||
|
require_soul_md_check: true
|
||||||
|
soul_md_path: SOUL.md
|
||||||
|
on_violation: block_and_notify
|
||||||
|
description: >
|
||||||
|
Before writing any code, the agent must demonstrate it has
|
||||||
|
read the issue, reviewed relevant existing code, and checked
|
||||||
|
SOUL.md for applicable doctrine. No speculative generation.
|
||||||
|
|
||||||
|
# 6. Completion integrity — no phantom completions
|
||||||
|
completion_checks:
|
||||||
|
enabled: true
|
||||||
|
require_test_evidence: true
|
||||||
|
require_ci_green: true
|
||||||
|
require_diff_matches_issue: true
|
||||||
|
require_no_unrelated_changes: true
|
||||||
|
on_violation: revert_and_notify
|
||||||
|
description: >
|
||||||
|
Post-task gate verifies the work actually addresses the
|
||||||
|
issue. Agents cannot close issues without evidence.
|
||||||
|
Unrelated changes in a PR trigger automatic rejection.
|
||||||
|
|
||||||
|
# 7. Communication discipline — no noise
|
||||||
|
communication:
|
||||||
|
enabled: true
|
||||||
|
max_comments_per_issue: 10
|
||||||
|
require_structured_updates: true
|
||||||
|
update_format: "status | what_changed | what_blocked | next_step"
|
||||||
|
prohibit_empty_updates: true
|
||||||
|
on_violation: warn
|
||||||
|
description: >
|
||||||
|
Issue comments must be structured and substantive.
|
||||||
|
Status-only comments without content are rejected.
|
||||||
|
Agents should update, not narrate.
|
||||||
|
|
||||||
|
# 8. Resource awareness — no runaway costs
|
||||||
|
resource_limits:
|
||||||
|
enabled: true
|
||||||
|
max_api_calls_per_task: 100
|
||||||
|
max_llm_tokens_per_task: 500000
|
||||||
|
max_task_duration_minutes: 60
|
||||||
|
on_violation: kill_and_notify
|
||||||
|
description: >
|
||||||
|
Hard limits on compute per task. If an agent hits these
|
||||||
|
limits, the task is killed and flagged for human review.
|
||||||
|
Prevents infinite loops and runaway API spending.
|
||||||
|
|
||||||
|
# ─── ESCALATION POLICY ───────────────────────────────────────────
|
||||||
|
|
||||||
|
escalation:
|
||||||
|
channels:
|
||||||
|
- gitea_issue_comment
|
||||||
|
- discord_webhook
|
||||||
|
severity_levels:
|
||||||
|
warn:
|
||||||
|
action: post_comment
|
||||||
|
notify: agent_only
|
||||||
|
block:
|
||||||
|
action: prevent_action
|
||||||
|
notify: agent_and_orchestrator
|
||||||
|
block_and_notify:
|
||||||
|
action: prevent_action
|
||||||
|
notify: agent_orchestrator_and_timmy
|
||||||
|
kill_and_notify:
|
||||||
|
action: terminate_task
|
||||||
|
notify: all_including_alexander
|
||||||
|
revert_and_notify:
|
||||||
|
action: revert_changes
|
||||||
|
notify: agent_orchestrator_and_timmy
|
||||||
|
|
||||||
|
# ─── AUDIT TRAIL ─────────────────────────────────────────────────
|
||||||
|
|
||||||
|
audit:
|
||||||
|
enabled: true
|
||||||
|
log_path: logs/guardrail-violations.jsonl
|
||||||
|
retention_days: 90
|
||||||
|
fields:
|
||||||
|
- timestamp
|
||||||
|
- agent
|
||||||
|
- constraint
|
||||||
|
- violation_type
|
||||||
|
- issue_number
|
||||||
|
- action_taken
|
||||||
|
- resolution
|
||||||
|
|
||||||
|
# ─── OVERRIDES ───────────────────────────────────────────────────
|
||||||
|
|
||||||
|
overrides:
|
||||||
|
# Only Timmy or Alexander can override guardrails
|
||||||
|
authorized_overriders:
|
||||||
|
- Timmy
|
||||||
|
- Alexander
|
||||||
|
override_mechanism: >
|
||||||
|
Post a comment on the issue with the format:
|
||||||
|
GUARDRAIL_OVERRIDE: <constraint_name> REASON: <explanation>
|
||||||
|
override_expiry_hours: 24
|
||||||
|
require_post_override_review: true
|
||||||
@@ -4,8 +4,8 @@ description: >
|
|||||||
agents. Decomposes large issues into smaller ones.
|
agents. Decomposes large issues into smaller ones.
|
||||||
|
|
||||||
model:
|
model:
|
||||||
preferred: claude-opus-4-6
|
preferred: kimi-k2.5
|
||||||
fallback: claude-sonnet-4-20250514
|
fallback: google/gemini-2.5-pro
|
||||||
max_turns: 20
|
max_turns: 20
|
||||||
temperature: 0.3
|
temperature: 0.3
|
||||||
|
|
||||||
@@ -50,7 +50,7 @@ system_prompt: |
|
|||||||
- codex-agent: cleanup, migration verification, dead-code removal, repo-boundary enforcement, workflow hardening
|
- codex-agent: cleanup, migration verification, dead-code removal, repo-boundary enforcement, workflow hardening
|
||||||
- groq: bounded implementation, tactical bug fixes, quick feature slices, small patches with clear acceptance criteria
|
- groq: bounded implementation, tactical bug fixes, quick feature slices, small patches with clear acceptance criteria
|
||||||
- manus: bounded support tasks, moderate-scope implementation, follow-through on already-scoped work
|
- manus: bounded support tasks, moderate-scope implementation, follow-through on already-scoped work
|
||||||
- claude: hard refactors, broad multi-file implementation, test-heavy changes after the scope is made precise
|
- kimi: hard refactors, broad multi-file implementation, test-heavy changes after the scope is made precise
|
||||||
- gemini: frontier architecture, research-heavy prototypes, long-range design thinking when a concrete implementation owner is not yet obvious
|
- gemini: frontier architecture, research-heavy prototypes, long-range design thinking when a concrete implementation owner is not yet obvious
|
||||||
- grok: adversarial testing, unusual edge cases, provocative review angles that still need another pass
|
- grok: adversarial testing, unusual edge cases, provocative review angles that still need another pass
|
||||||
5. Decompose any issue touching >5 files or crossing repo boundaries into smaller issues before assigning execution
|
5. Decompose any issue touching >5 files or crossing repo boundaries into smaller issues before assigning execution
|
||||||
@@ -63,6 +63,6 @@ system_prompt: |
|
|||||||
- Search for existing issues or PRs covering the same request before assigning anything. If a likely duplicate exists, link it and do not create or route duplicate work.
|
- Search for existing issues or PRs covering the same request before assigning anything. If a likely duplicate exists, link it and do not create or route duplicate work.
|
||||||
- Do not assign open-ended ideation to implementation agents.
|
- Do not assign open-ended ideation to implementation agents.
|
||||||
- Do not assign routine backlog maintenance to Timmy.
|
- Do not assign routine backlog maintenance to Timmy.
|
||||||
- Do not assign wide speculative backlog generation to codex-agent, groq, manus, or claude.
|
- Do not assign wide speculative backlog generation to codex-agent, groq, or manus.
|
||||||
- Route archive/history/context-digestion work to ezra or KimiClaw before routing it to a builder.
|
- Route archive/history/context-digestion work to ezra or KimiClaw before routing it to a builder.
|
||||||
- Route “who should do this?” and “what is the next move?” questions to allegro.
|
- Route “who should do this?” and “what is the next move?” questions to allegro.
|
||||||
|
|||||||
@@ -4,8 +4,8 @@ description: >
|
|||||||
comments on problems. The merge bot replacement.
|
comments on problems. The merge bot replacement.
|
||||||
|
|
||||||
model:
|
model:
|
||||||
preferred: claude-opus-4-6
|
preferred: kimi-k2.5
|
||||||
fallback: claude-sonnet-4-20250514
|
fallback: google/gemini-2.5-pro
|
||||||
max_turns: 20
|
max_turns: 20
|
||||||
temperature: 0.2
|
temperature: 0.2
|
||||||
|
|
||||||
|
|||||||
@@ -4,8 +4,8 @@ description: >
|
|||||||
Well-scoped: 1-3 files per task, clear acceptance criteria.
|
Well-scoped: 1-3 files per task, clear acceptance criteria.
|
||||||
|
|
||||||
model:
|
model:
|
||||||
preferred: claude-opus-4-6
|
preferred: kimi-k2.5
|
||||||
fallback: claude-sonnet-4-20250514
|
fallback: google/gemini-2.5-pro
|
||||||
max_turns: 30
|
max_turns: 30
|
||||||
temperature: 0.3
|
temperature: 0.3
|
||||||
|
|
||||||
|
|||||||
@@ -4,8 +4,8 @@ description: >
|
|||||||
dependency issues. Files findings as Gitea issues.
|
dependency issues. Files findings as Gitea issues.
|
||||||
|
|
||||||
model:
|
model:
|
||||||
preferred: claude-opus-4-6
|
preferred: kimi-k2.5
|
||||||
fallback: claude-opus-4-6
|
fallback: google/gemini-2.5-pro
|
||||||
max_turns: 40
|
max_turns: 40
|
||||||
temperature: 0.2
|
temperature: 0.2
|
||||||
|
|
||||||
|
|||||||
@@ -4,8 +4,8 @@ description: >
|
|||||||
writes meaningful tests, verifies they pass.
|
writes meaningful tests, verifies they pass.
|
||||||
|
|
||||||
model:
|
model:
|
||||||
preferred: claude-opus-4-6
|
preferred: kimi-k2.5
|
||||||
fallback: claude-sonnet-4-20250514
|
fallback: google/gemini-2.5-pro
|
||||||
max_turns: 30
|
max_turns: 30
|
||||||
temperature: 0.3
|
temperature: 0.3
|
||||||
|
|
||||||
|
|||||||
@@ -5,8 +5,8 @@ description: >
|
|||||||
and consistency verification.
|
and consistency verification.
|
||||||
|
|
||||||
model:
|
model:
|
||||||
preferred: claude-opus-4-6
|
preferred: kimi-k2.5
|
||||||
fallback: claude-sonnet-4-20250514
|
fallback: google/gemini-2.5-pro
|
||||||
max_turns: 12
|
max_turns: 12
|
||||||
temperature: 0.1
|
temperature: 0.1
|
||||||
|
|
||||||
|
|||||||
60
scripts/README.md
Normal file
60
scripts/README.md
Normal file
@@ -0,0 +1,60 @@
|
|||||||
|
# Gemini Sovereign Infrastructure Suite
|
||||||
|
|
||||||
|
This directory contains the core systems of the Gemini Sovereign Infrastructure, designed to systematize fleet operations, governance, and architectural integrity.
|
||||||
|
|
||||||
|
## Principles
|
||||||
|
|
||||||
|
1. **Systems, not Scripts**: We build frameworks that solve classes of problems, not one-off fixes.
|
||||||
|
2. **Sovereignty First**: All tools are designed to run locally or on owned VPSes. No cloud dependencies.
|
||||||
|
3. **Von Neumann as Code**: Infrastructure should be self-replicating and automated.
|
||||||
|
4. **Continuous Governance**: Quality is enforced by code (linters, gates), not just checklists.
|
||||||
|
|
||||||
|
## Tools
|
||||||
|
|
||||||
|
### [OPS] Provisioning & Fleet Management
|
||||||
|
|
||||||
|
- **`provision_wizard.py`**: Automates the creation of a new Wizard node from zero.
|
||||||
|
- Creates DigitalOcean droplet.
|
||||||
|
- Installs and builds `llama.cpp`.
|
||||||
|
- Downloads GGUF models.
|
||||||
|
- Sets up `systemd` services and health checks.
|
||||||
|
- **`fleet_llama.py`**: Unified management of `llama-server` instances across the fleet.
|
||||||
|
- `status`: Real-time health and model monitoring.
|
||||||
|
- `restart`: Remote service restart via SSH.
|
||||||
|
- `swap`: Hot-swapping GGUF models on remote nodes.
|
||||||
|
- **`skill_installer.py`**: Packages and deploys Hermes skills to remote wizards.
|
||||||
|
- **`model_eval.py`**: Benchmarks GGUF models for speed and quality before deployment.
|
||||||
|
- **`phase_tracker.py`**: Tracks the fleet's progress through the Paperclips-inspired evolution arc.
|
||||||
|
- **`cross_repo_test.py`**: Verifies the fleet works as a system by running tests across all core repositories.
|
||||||
|
- **`self_healing.py`**: Auto-detects and fixes common failures across the fleet.
|
||||||
|
- **`agent_dispatch.py`**: Unified framework for tasking agents across the fleet.
|
||||||
|
- **`telemetry.py`**: Operational visibility without cloud dependencies.
|
||||||
|
- **`gitea_webhook_handler.py`**: Handles real-time events from Gitea to coordinate fleet actions.
|
||||||
|
|
||||||
|
### [ARCH] Governance & Architecture
|
||||||
|
|
||||||
|
- **`architecture_linter_v2.py`**: Automated enforcement of architectural boundaries.
|
||||||
|
- Enforces sidecar boundaries (no sovereign code in `hermes-agent`).
|
||||||
|
- Prevents hardcoded IPs and committed secrets.
|
||||||
|
- Ensures `SOUL.md` and `README.md` standards.
|
||||||
|
- **`adr_manager.py`**: Streamlines the creation and tracking of Architecture Decision Records.
|
||||||
|
- `new`: Scaffolds a new ADR from a template.
|
||||||
|
- `list`: Provides a chronological view of architectural evolution.
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
Most tools require `DIGITALOCEAN_TOKEN` and SSH access to the fleet.
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Provision a new node
|
||||||
|
python3 scripts/provision_wizard.py --name fenrir --model qwen2.5-coder-7b
|
||||||
|
|
||||||
|
# Check fleet status
|
||||||
|
python3 scripts/fleet_llama.py status
|
||||||
|
|
||||||
|
# Audit architectural integrity
|
||||||
|
python3 scripts/architecture_linter_v2.py
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
*Built by Gemini — The Builder, The Systematizer, The Force Multiplier.*
|
||||||
113
scripts/adr_manager.py
Normal file
113
scripts/adr_manager.py
Normal file
@@ -0,0 +1,113 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[ARCH] ADR Manager
|
||||||
|
Part of the Gemini Sovereign Governance System.
|
||||||
|
|
||||||
|
Helps create and manage Architecture Decision Records (ADRs).
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import datetime
|
||||||
|
import argparse
|
||||||
|
|
||||||
|
ADR_DIR = "docs/adr"
|
||||||
|
TEMPLATE_FILE = "docs/adr/ADR_TEMPLATE.md"
|
||||||
|
|
||||||
|
class ADRManager:
|
||||||
|
def __init__(self):
|
||||||
|
# Ensure we are in the repo root or can find docs/adr
|
||||||
|
if not os.path.exists(ADR_DIR):
|
||||||
|
# Try to find it relative to the script
|
||||||
|
script_dir = os.path.dirname(os.path.abspath(__file__))
|
||||||
|
repo_root = os.path.dirname(script_dir)
|
||||||
|
self.adr_dir = os.path.join(repo_root, ADR_DIR)
|
||||||
|
self.template_file = os.path.join(repo_root, TEMPLATE_FILE)
|
||||||
|
else:
|
||||||
|
self.adr_dir = ADR_DIR
|
||||||
|
self.template_file = TEMPLATE_FILE
|
||||||
|
|
||||||
|
if not os.path.exists(self.adr_dir):
|
||||||
|
os.makedirs(self.adr_dir)
|
||||||
|
|
||||||
|
def get_next_number(self):
|
||||||
|
files = [f for f in os.listdir(self.adr_dir) if f.endswith(".md") and f[0].isdigit()]
|
||||||
|
if not files:
|
||||||
|
return 1
|
||||||
|
numbers = [int(f.split("-")[0]) for f in files]
|
||||||
|
return max(numbers) + 1
|
||||||
|
|
||||||
|
def create_adr(self, title: str):
|
||||||
|
num = self.get_next_number()
|
||||||
|
slug = title.lower().replace(" ", "-").replace("/", "-")
|
||||||
|
filename = f"{num:04d}-{slug}.md"
|
||||||
|
filepath = os.path.join(self.adr_dir, filename)
|
||||||
|
|
||||||
|
date = datetime.date.today().isoformat()
|
||||||
|
|
||||||
|
template = ""
|
||||||
|
if os.path.exists(self.template_file):
|
||||||
|
with open(self.template_file, "r") as f:
|
||||||
|
template = f.read()
|
||||||
|
else:
|
||||||
|
template = """# {num}. {title}
|
||||||
|
|
||||||
|
Date: {date}
|
||||||
|
|
||||||
|
## Status
|
||||||
|
|
||||||
|
Proposed
|
||||||
|
|
||||||
|
## Context
|
||||||
|
|
||||||
|
What is the problem we are solving?
|
||||||
|
|
||||||
|
## Decision
|
||||||
|
|
||||||
|
What is the decision we made?
|
||||||
|
|
||||||
|
## Consequences
|
||||||
|
|
||||||
|
What are the positive and negative consequences?
|
||||||
|
"""
|
||||||
|
|
||||||
|
content = template.replace("{num}", f"{num:04d}")
|
||||||
|
content = content.replace("{title}", title)
|
||||||
|
content = content.replace("{date}", date)
|
||||||
|
|
||||||
|
with open(filepath, "w") as f:
|
||||||
|
f.write(content)
|
||||||
|
|
||||||
|
print(f"[SUCCESS] Created ADR: {filepath}")
|
||||||
|
|
||||||
|
def list_adrs(self):
|
||||||
|
files = sorted([f for f in os.listdir(self.adr_dir) if f.endswith(".md") and f[0].isdigit()])
|
||||||
|
print(f"{'NUM':<6} {'TITLE'}")
|
||||||
|
print("-" * 40)
|
||||||
|
for f in files:
|
||||||
|
num = f.split("-")[0]
|
||||||
|
title = f.split("-", 1)[1].replace(".md", "").replace("-", " ").title()
|
||||||
|
print(f"{num:<6} {title}")
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Gemini ADR Manager")
|
||||||
|
subparsers = parser.add_subparsers(dest="command")
|
||||||
|
|
||||||
|
create_parser = subparsers.add_parser("new", help="Create a new ADR")
|
||||||
|
create_parser.add_argument("title", help="Title of the ADR")
|
||||||
|
|
||||||
|
subparsers.add_parser("list", help="List all ADRs")
|
||||||
|
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
manager = ADRManager()
|
||||||
|
|
||||||
|
if args.command == "new":
|
||||||
|
manager.create_adr(args.title)
|
||||||
|
elif args.command == "list":
|
||||||
|
manager.list_adrs()
|
||||||
|
else:
|
||||||
|
parser.print_help()
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
65
scripts/agent_dispatch.py
Normal file
65
scripts/agent_dispatch.py
Normal file
@@ -0,0 +1,65 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[OPS] Agent Dispatch Framework
|
||||||
|
Part of the Gemini Sovereign Infrastructure Suite.
|
||||||
|
|
||||||
|
Replaces ad-hoc dispatch scripts with a unified framework for tasking agents.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import argparse
|
||||||
|
|
||||||
|
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||||
|
if SCRIPT_DIR not in sys.path:
|
||||||
|
sys.path.insert(0, SCRIPT_DIR)
|
||||||
|
|
||||||
|
from ssh_trust import VerifiedSSHExecutor
|
||||||
|
|
||||||
|
# --- CONFIGURATION ---
|
||||||
|
FLEET = {
|
||||||
|
"allegro": "167.99.126.228",
|
||||||
|
"bezalel": "159.203.146.185"
|
||||||
|
}
|
||||||
|
|
||||||
|
class Dispatcher:
|
||||||
|
def __init__(self, executor=None):
|
||||||
|
self.executor = executor or VerifiedSSHExecutor()
|
||||||
|
|
||||||
|
def log(self, message: str):
|
||||||
|
print(f"[*] {message}")
|
||||||
|
|
||||||
|
def dispatch(self, host: str, agent_name: str, task: str):
|
||||||
|
self.log(f"Dispatching task to {agent_name} on {host}...")
|
||||||
|
|
||||||
|
ip = FLEET[host]
|
||||||
|
|
||||||
|
try:
|
||||||
|
res = self.executor.run(
|
||||||
|
ip,
|
||||||
|
['python3', 'run_agent.py', '--agent', agent_name, '--task', task],
|
||||||
|
cwd='/opt/hermes',
|
||||||
|
timeout=30,
|
||||||
|
)
|
||||||
|
if res.returncode == 0:
|
||||||
|
self.log(f"[SUCCESS] {agent_name} completed task.")
|
||||||
|
print(res.stdout)
|
||||||
|
else:
|
||||||
|
self.log(f"[FAILURE] {agent_name} failed task.")
|
||||||
|
print(res.stderr)
|
||||||
|
except Exception as e:
|
||||||
|
self.log(f"[ERROR] Dispatch failed: {e}")
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Gemini Agent Dispatcher")
|
||||||
|
parser.add_argument("host", choices=list(FLEET.keys()), help="Host to dispatch to")
|
||||||
|
parser.add_argument("agent", help="Agent name")
|
||||||
|
parser.add_argument("task", help="Task description")
|
||||||
|
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
dispatcher = Dispatcher()
|
||||||
|
dispatcher.dispatch(args.host, args.agent, args.task)
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
126
scripts/agent_guardrails.py
Normal file
126
scripts/agent_guardrails.py
Normal file
@@ -0,0 +1,126 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
agent_guardrails.py — Sovereign Agent Guardrails for the Timmy Foundation.
|
||||||
|
|
||||||
|
Scans agent logs and conversation trajectories for:
|
||||||
|
1. System Prompt Leakage — detecting if the agent revealed its internal instructions.
|
||||||
|
2. Jailbreak Compliance — detecting if the agent responded to "GODMODE", "DAN", etc.
|
||||||
|
3. PII Leakage — detecting if secrets or sensitive data were output.
|
||||||
|
|
||||||
|
Part of the Sovereign Infrastructure Suite.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import re
|
||||||
|
import sys
|
||||||
|
import glob
|
||||||
|
import logging
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import List, Dict, Tuple
|
||||||
|
|
||||||
|
# Patterns adapted from hermes-agent/agent/input_sanitizer.py
|
||||||
|
EXTRACTION_PATTERNS = [
|
||||||
|
r"repeat\s+the\s+words\s+above",
|
||||||
|
r"repeat\s+your\s+(?:system\s+|initial\s+)?instructions",
|
||||||
|
r"what\s+is\s+your\s+(?:system\s+|initial\s+)?prompt",
|
||||||
|
r"show\s+me\s+your\s+(?:system\s+|initial\s+)?prompt",
|
||||||
|
r"print\s+your\s+(?:instructions|prompt|system\s+prompt)",
|
||||||
|
r"output\s+your\s+(?:initial|system)\s+prompt",
|
||||||
|
]
|
||||||
|
|
||||||
|
# Patterns that indicate the agent MIGHT be leaking its prompt
|
||||||
|
LEAKAGE_INDICATORS = [
|
||||||
|
r"you\s+are\s+a\s+helpful\s+assistant",
|
||||||
|
r"your\s+goal\s+is\s+to",
|
||||||
|
r"you\s+must\s+not",
|
||||||
|
r"here\s+are\s+your\s+instructions",
|
||||||
|
r"my\s+system\s+prompt\s+is",
|
||||||
|
r"i\s+was\s+told\s+to",
|
||||||
|
]
|
||||||
|
|
||||||
|
# Patterns for secrets (adapted from redact.py)
|
||||||
|
SECRET_PATTERNS = [
|
||||||
|
r"sk-[A-Za-z0-9_-]{20,}",
|
||||||
|
r"ghp_[A-Za-z0-9]{20,}",
|
||||||
|
r"AIza[A-Za-z0-9_-]{30,}",
|
||||||
|
]
|
||||||
|
|
||||||
|
AGENT_LOG_PATHS = [
|
||||||
|
"/root/wizards/*/home/logs/*.log",
|
||||||
|
"/root/wizards/*/logs/*.log",
|
||||||
|
"/root/wizards/*/.hermes/logs/*.log",
|
||||||
|
]
|
||||||
|
|
||||||
|
class GuardrailAuditor:
|
||||||
|
def __init__(self):
|
||||||
|
self.extraction_re = [re.compile(p, re.IGNORECASE) for p in EXTRACTION_PATTERNS]
|
||||||
|
self.leakage_re = [re.compile(p, re.IGNORECASE) for p in LEAKAGE_INDICATORS]
|
||||||
|
self.secret_re = [re.compile(p, re.IGNORECASE) for p in SECRET_PATTERNS]
|
||||||
|
|
||||||
|
def find_logs(self) -> List[Path]:
|
||||||
|
files = []
|
||||||
|
for pattern in AGENT_LOG_PATHS:
|
||||||
|
for p in glob.glob(pattern):
|
||||||
|
files.append(Path(p))
|
||||||
|
return files
|
||||||
|
|
||||||
|
def audit_file(self, path: Path) -> List[Dict]:
|
||||||
|
findings = []
|
||||||
|
try:
|
||||||
|
with open(path, "r", errors="ignore") as f:
|
||||||
|
lines = f.readlines()
|
||||||
|
for i, line in enumerate(lines):
|
||||||
|
# Check for extraction attempts (User side)
|
||||||
|
for p in self.extraction_re:
|
||||||
|
if p.search(line):
|
||||||
|
findings.append({
|
||||||
|
"type": "EXTRACTION_ATTEMPT",
|
||||||
|
"line": i + 1,
|
||||||
|
"content": line.strip()[:100],
|
||||||
|
"severity": "MEDIUM"
|
||||||
|
})
|
||||||
|
|
||||||
|
# Check for potential leakage (Assistant side)
|
||||||
|
for p in self.leakage_re:
|
||||||
|
if p.search(line):
|
||||||
|
findings.append({
|
||||||
|
"type": "POTENTIAL_LEAKAGE",
|
||||||
|
"line": i + 1,
|
||||||
|
"content": line.strip()[:100],
|
||||||
|
"severity": "HIGH"
|
||||||
|
})
|
||||||
|
|
||||||
|
# Check for secrets
|
||||||
|
for p in self.secret_re:
|
||||||
|
if p.search(line):
|
||||||
|
findings.append({
|
||||||
|
"type": "SECRET_EXPOSURE",
|
||||||
|
"line": i + 1,
|
||||||
|
"content": "[REDACTED]",
|
||||||
|
"severity": "CRITICAL"
|
||||||
|
})
|
||||||
|
except Exception as e:
|
||||||
|
print(f"Error reading {path}: {e}")
|
||||||
|
return findings
|
||||||
|
|
||||||
|
def run(self):
|
||||||
|
print("--- Sovereign Agent Guardrail Audit ---")
|
||||||
|
logs = self.find_logs()
|
||||||
|
print(f"Scanning {len(logs)} log files...")
|
||||||
|
|
||||||
|
total_findings = 0
|
||||||
|
for log in logs:
|
||||||
|
findings = self.audit_file(log)
|
||||||
|
if findings:
|
||||||
|
print(f"\nFindings in {log}:")
|
||||||
|
for f in findings:
|
||||||
|
print(f" [{f['severity']}] {f['type']} at line {f['line']}: {f['content']}")
|
||||||
|
total_findings += 1
|
||||||
|
|
||||||
|
print(f"\nAudit complete. Total findings: {total_findings}")
|
||||||
|
if total_findings > 0:
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
auditor = GuardrailAuditor()
|
||||||
|
auditor.run()
|
||||||
@@ -9,7 +9,7 @@ import re
|
|||||||
SOVEREIGN_RULES = [
|
SOVEREIGN_RULES = [
|
||||||
(r"https?://(api\.openai\.com|api\.anthropic\.com)", "CRITICAL: External cloud API detected. Use local custom_provider instead."),
|
(r"https?://(api\.openai\.com|api\.anthropic\.com)", "CRITICAL: External cloud API detected. Use local custom_provider instead."),
|
||||||
(r"provider: (openai|anthropic)", "WARNING: Direct cloud provider used. Ensure fallback_model is configured."),
|
(r"provider: (openai|anthropic)", "WARNING: Direct cloud provider used. Ensure fallback_model is configured."),
|
||||||
(r"api_key: ['"][^'"\s]{10,}['"]", "SECURITY: Hardcoded API key detected. Use environment variables.")
|
(r"api_key:\s*['\"][A-Za-z0-9_\-]{16,}['\"]", "SECURITY: Hardcoded API key detected. Use environment variables.")
|
||||||
]
|
]
|
||||||
|
|
||||||
def lint_file(path):
|
def lint_file(path):
|
||||||
|
|||||||
237
scripts/architecture_linter_v2.py
Normal file
237
scripts/architecture_linter_v2.py
Normal file
@@ -0,0 +1,237 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[ARCH] Architecture Linter v2
|
||||||
|
Part of the Gemini Sovereign Governance System.
|
||||||
|
|
||||||
|
Enforces architectural boundaries, security, and documentation standards
|
||||||
|
across the Timmy Foundation fleet.
|
||||||
|
|
||||||
|
Refs: #437 — repo-aware, test-backed, CI-enforced.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import os
|
||||||
|
import re
|
||||||
|
import sys
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
# --- CONFIGURATION ---
|
||||||
|
|
||||||
|
SOVEREIGN_KEYWORDS = ["mempalace", "sovereign_store", "tirith", "bezalel", "nexus"]
|
||||||
|
|
||||||
|
# IP addresses (skip 127.0.0.1, 0.0.0.0, 10.x.x.x, 172.16-31.x.x, 192.168.x.x)
|
||||||
|
IP_REGEX = r'\b(?!(?:127|10|192\.168|172\.(?:1[6-9]|2\d|3[01]))\.)' \
|
||||||
|
r'(?:\d{1,3}\.){3}\d{1,3}\b'
|
||||||
|
|
||||||
|
# API key / secret patterns — catches openai-, sk-, anthropic-, AKIA, etc.
|
||||||
|
API_KEY_PATTERNS = [
|
||||||
|
r'sk-[A-Za-z0-9]{20,}', # OpenAI-style
|
||||||
|
r'sk-ant-[A-Za-z0-9\-]{20,}', # Anthropic
|
||||||
|
r'AKIA[A-Z0-9]{16}', # AWS access key
|
||||||
|
r'ghp_[A-Za-z0-9]{36}', # GitHub PAT
|
||||||
|
r'glpat-[A-Za-z0-9\-]{20,}', # GitLab PAT
|
||||||
|
r'(?:api[_-]?key|secret|token)\s*[:=]\s*["\'][A-Za-z0-9_\-]{16,}["\']',
|
||||||
|
]
|
||||||
|
|
||||||
|
# Sovereignty rules (carried from v1)
|
||||||
|
SOVEREIGN_RULES = [
|
||||||
|
(r'https?://api\.openai\.com', 'External cloud API: api.openai.com. Use local custom_provider.'),
|
||||||
|
(r'https?://api\.anthropic\.com', 'External cloud API: api.anthropic.com. Use local custom_provider.'),
|
||||||
|
(r'provider:\s*(?:openai|anthropic)\b', 'Direct cloud provider. Ensure fallback_model is configured.'),
|
||||||
|
]
|
||||||
|
|
||||||
|
# File extensions to scan
|
||||||
|
SCAN_EXTENSIONS = {'.py', '.ts', '.tsx', '.js', '.yaml', '.yml', '.json', '.env', '.sh', '.cfg', '.toml'}
|
||||||
|
SKIP_DIRS = {'.git', 'node_modules', '__pycache__', '.venv', 'venv', '.tox', '.eggs'}
|
||||||
|
|
||||||
|
|
||||||
|
class LinterResult:
|
||||||
|
"""Structured result container for programmatic access."""
|
||||||
|
|
||||||
|
def __init__(self, repo_path: str, repo_name: str):
|
||||||
|
self.repo_path = repo_path
|
||||||
|
self.repo_name = repo_name
|
||||||
|
self.errors: list[str] = []
|
||||||
|
self.warnings: list[str] = []
|
||||||
|
|
||||||
|
@property
|
||||||
|
def passed(self) -> bool:
|
||||||
|
return len(self.errors) == 0
|
||||||
|
|
||||||
|
@property
|
||||||
|
def violation_count(self) -> int:
|
||||||
|
return len(self.errors)
|
||||||
|
|
||||||
|
def summary(self) -> str:
|
||||||
|
lines = [f"--- Architecture Linter v2: {self.repo_name} ---"]
|
||||||
|
for w in self.warnings:
|
||||||
|
lines.append(f" [W] {w}")
|
||||||
|
for e in self.errors:
|
||||||
|
lines.append(f" [E] {e}")
|
||||||
|
status = "PASSED" if self.passed else f"FAILED ({self.violation_count} violations)"
|
||||||
|
lines.append(f"\nResult: {status}")
|
||||||
|
return '\n'.join(lines)
|
||||||
|
|
||||||
|
|
||||||
|
class Linter:
|
||||||
|
def __init__(self, repo_path: str):
|
||||||
|
self.repo_path = Path(repo_path).resolve()
|
||||||
|
if not self.repo_path.is_dir():
|
||||||
|
raise FileNotFoundError(f"Repository path does not exist: {self.repo_path}")
|
||||||
|
self.repo_name = self.repo_path.name
|
||||||
|
self.result = LinterResult(str(self.repo_path), self.repo_name)
|
||||||
|
|
||||||
|
# --- helpers ---
|
||||||
|
|
||||||
|
def _scan_files(self, extensions=None):
|
||||||
|
"""Yield (Path, content) for files matching *extensions*."""
|
||||||
|
exts = extensions or SCAN_EXTENSIONS
|
||||||
|
for root, dirs, files in os.walk(self.repo_path):
|
||||||
|
dirs[:] = [d for d in dirs if d not in SKIP_DIRS]
|
||||||
|
for fname in files:
|
||||||
|
if Path(fname).suffix in exts:
|
||||||
|
if fname == '.env.example':
|
||||||
|
continue
|
||||||
|
fpath = Path(root) / fname
|
||||||
|
try:
|
||||||
|
content = fpath.read_text(errors='ignore')
|
||||||
|
except Exception:
|
||||||
|
continue
|
||||||
|
yield fpath, content
|
||||||
|
|
||||||
|
def _line_no(self, content: str, offset: int) -> int:
|
||||||
|
return content.count('\n', 0, offset) + 1
|
||||||
|
|
||||||
|
# --- checks ---
|
||||||
|
|
||||||
|
def check_sidecar_boundary(self):
|
||||||
|
"""No sovereign code in hermes-agent (sidecar boundary)."""
|
||||||
|
if self.repo_name != 'hermes-agent':
|
||||||
|
return
|
||||||
|
for fpath, content in self._scan_files():
|
||||||
|
for kw in SOVEREIGN_KEYWORDS:
|
||||||
|
if kw in content.lower():
|
||||||
|
rel = str(fpath.relative_to(self.repo_path))
|
||||||
|
self.result.errors.append(
|
||||||
|
f"Sovereign keyword '{kw}' in hermes-agent violates sidecar boundary. [{rel}]"
|
||||||
|
)
|
||||||
|
|
||||||
|
def check_hardcoded_ips(self):
|
||||||
|
"""No hardcoded public IPs — use DNS or env vars."""
|
||||||
|
for fpath, content in self._scan_files():
|
||||||
|
for m in re.finditer(IP_REGEX, content):
|
||||||
|
ip = m.group()
|
||||||
|
# skip private ranges already handled by lookahead, and 0.0.0.0
|
||||||
|
if ip.startswith('0.'):
|
||||||
|
continue
|
||||||
|
line = self._line_no(content, m.start())
|
||||||
|
rel = str(fpath.relative_to(self.repo_path))
|
||||||
|
self.result.errors.append(
|
||||||
|
f"Hardcoded IP '{ip}'. Use DNS or env vars. [{rel}:{line}]"
|
||||||
|
)
|
||||||
|
|
||||||
|
def check_api_keys(self):
|
||||||
|
"""No cloud API keys / secrets committed."""
|
||||||
|
for fpath, content in self._scan_files():
|
||||||
|
for pattern in API_KEY_PATTERNS:
|
||||||
|
for m in re.finditer(pattern, content, re.IGNORECASE):
|
||||||
|
line = self._line_no(content, m.start())
|
||||||
|
rel = str(fpath.relative_to(self.repo_path))
|
||||||
|
self.result.errors.append(
|
||||||
|
f"Potential secret / API key detected. [{rel}:{line}]"
|
||||||
|
)
|
||||||
|
|
||||||
|
def check_sovereignty_rules(self):
|
||||||
|
"""V1 sovereignty rules: no direct cloud API endpoints or providers."""
|
||||||
|
for fpath, content in self._scan_files({'.py', '.ts', '.tsx', '.js', '.yaml', '.yml'}):
|
||||||
|
for pattern, msg in SOVEREIGN_RULES:
|
||||||
|
for m in re.finditer(pattern, content):
|
||||||
|
line = self._line_no(content, m.start())
|
||||||
|
rel = str(fpath.relative_to(self.repo_path))
|
||||||
|
self.result.errors.append(f"{msg} [{rel}:{line}]")
|
||||||
|
|
||||||
|
def check_soul_canonical(self):
|
||||||
|
"""SOUL.md must exist exactly in timmy-config root."""
|
||||||
|
soul_path = self.repo_path / 'SOUL.md'
|
||||||
|
if self.repo_name == 'timmy-config':
|
||||||
|
if not soul_path.exists():
|
||||||
|
self.result.errors.append(
|
||||||
|
'SOUL.md missing from canonical location (timmy-config root).'
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
if soul_path.exists():
|
||||||
|
self.result.errors.append(
|
||||||
|
'SOUL.md found in non-canonical repo. Must live only in timmy-config.'
|
||||||
|
)
|
||||||
|
|
||||||
|
def check_readme(self):
|
||||||
|
"""Every repo must have a substantive README."""
|
||||||
|
readme = self.repo_path / 'README.md'
|
||||||
|
if not readme.exists():
|
||||||
|
self.result.errors.append('README.md is missing.')
|
||||||
|
else:
|
||||||
|
content = readme.read_text(errors='ignore')
|
||||||
|
if len(content.strip()) < 50:
|
||||||
|
self.result.warnings.append(
|
||||||
|
'README.md is very short (<50 chars). Provide current truth about the repo.'
|
||||||
|
)
|
||||||
|
|
||||||
|
# --- runner ---
|
||||||
|
|
||||||
|
def run(self) -> LinterResult:
|
||||||
|
"""Execute all checks and return the result."""
|
||||||
|
self.check_sidecar_boundary()
|
||||||
|
self.check_hardcoded_ips()
|
||||||
|
self.check_api_keys()
|
||||||
|
self.check_sovereignty_rules()
|
||||||
|
self.check_soul_canonical()
|
||||||
|
self.check_readme()
|
||||||
|
return self.result
|
||||||
|
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(
|
||||||
|
description='Gemini Architecture Linter v2 — repo-aware sovereignty gate.'
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
'repo_path', nargs='?', default='.',
|
||||||
|
help='Path to the repository to lint (default: cwd).',
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
'--repo', dest='repo_flag', default=None,
|
||||||
|
help='Explicit repo path (alias for positional arg).',
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
'--json', dest='json_output', action='store_true',
|
||||||
|
help='Emit machine-readable JSON instead of human text.',
|
||||||
|
)
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
path = args.repo_flag if args.repo_flag else args.repo_path
|
||||||
|
|
||||||
|
try:
|
||||||
|
linter = Linter(path)
|
||||||
|
except FileNotFoundError as exc:
|
||||||
|
print(f"ERROR: {exc}", file=sys.stderr)
|
||||||
|
sys.exit(2)
|
||||||
|
|
||||||
|
result = linter.run()
|
||||||
|
|
||||||
|
if args.json_output:
|
||||||
|
import json as _json
|
||||||
|
out = {
|
||||||
|
'repo': result.repo_name,
|
||||||
|
'passed': result.passed,
|
||||||
|
'violation_count': result.violation_count,
|
||||||
|
'errors': result.errors,
|
||||||
|
'warnings': result.warnings,
|
||||||
|
}
|
||||||
|
print(_json.dumps(out, indent=2))
|
||||||
|
else:
|
||||||
|
print(result.summary())
|
||||||
|
|
||||||
|
sys.exit(0 if result.passed else 1)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
main()
|
||||||
11
scripts/captcha_bypass_handler.py
Normal file
11
scripts/captcha_bypass_handler.py
Normal file
@@ -0,0 +1,11 @@
|
|||||||
|
import json
|
||||||
|
from hermes_tools import browser_navigate, browser_vision
|
||||||
|
|
||||||
|
def bypass_captcha():
|
||||||
|
analysis = browser_vision(
|
||||||
|
question="Solve the CAPTCHA on the current page. Provide the solution text or coordinate clicks required. Provide a PASS/FAIL."
|
||||||
|
)
|
||||||
|
return {"status": "PASS" if "PASS" in analysis.upper() else "FAIL", "solution": analysis}
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
print(json.dumps(bypass_captcha(), indent=2))
|
||||||
87
scripts/ci_automation_gate.py
Normal file
87
scripts/ci_automation_gate.py
Normal file
@@ -0,0 +1,87 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
ci_automation_gate.py — Automated Quality Gate for Timmy Foundation CI.
|
||||||
|
|
||||||
|
Enforces:
|
||||||
|
1. The 10-line Rule — functions should ideally be under 10 lines (warn at 20, fail at 50).
|
||||||
|
2. Complexity Check — basic cyclomatic complexity check.
|
||||||
|
3. Auto-fixable Linting — trailing whitespace, missing final newlines.
|
||||||
|
|
||||||
|
Used as a pre-merge gate.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import re
|
||||||
|
import argparse
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
class QualityGate:
|
||||||
|
def __init__(self, fix=False):
|
||||||
|
self.fix = fix
|
||||||
|
self.failures = 0
|
||||||
|
self.warnings = 0
|
||||||
|
|
||||||
|
def check_file(self, path: Path):
|
||||||
|
if path.suffix not in (".js", ".ts", ".py"):
|
||||||
|
return
|
||||||
|
|
||||||
|
with open(path, "r") as f:
|
||||||
|
lines = f.readlines()
|
||||||
|
|
||||||
|
new_lines = []
|
||||||
|
changed = False
|
||||||
|
|
||||||
|
# 1. Basic Linting
|
||||||
|
for line in lines:
|
||||||
|
cleaned = line.rstrip() + "\n"
|
||||||
|
if cleaned != line:
|
||||||
|
changed = True
|
||||||
|
new_lines.append(cleaned)
|
||||||
|
|
||||||
|
if lines and not lines[-1].endswith("\n"):
|
||||||
|
new_lines[-1] = new_lines[-1] + "\n"
|
||||||
|
changed = True
|
||||||
|
|
||||||
|
if changed and self.fix:
|
||||||
|
with open(path, "w") as f:
|
||||||
|
f.writelines(new_lines)
|
||||||
|
print(f" [FIXED] {path}: Cleaned whitespace and newlines.")
|
||||||
|
elif changed:
|
||||||
|
print(f" [WARN] {path}: Has trailing whitespace or missing final newline.")
|
||||||
|
self.warnings += 1
|
||||||
|
|
||||||
|
# 2. Function Length Check (Simple regex-based)
|
||||||
|
content = "".join(new_lines)
|
||||||
|
if path.suffix in (".js", ".ts"):
|
||||||
|
# Match function blocks
|
||||||
|
functions = re.findall(r"function\s+\w+\s*\(.*?\)\s*\{([\s\S]*?)\}", content)
|
||||||
|
for i, func in enumerate(functions):
|
||||||
|
length = func.count("\n")
|
||||||
|
if length > 50:
|
||||||
|
print(f" [FAIL] {path}: Function {i} is too long ({length} lines).")
|
||||||
|
self.failures += 1
|
||||||
|
elif length > 20:
|
||||||
|
print(f" [WARN] {path}: Function {i} is getting long ({length} lines).")
|
||||||
|
self.warnings += 1
|
||||||
|
|
||||||
|
def run(self, directory: str):
|
||||||
|
print(f"--- Quality Gate: {directory} ---")
|
||||||
|
for root, _, files in os.walk(directory):
|
||||||
|
if "node_modules" in root or ".git" in root:
|
||||||
|
continue
|
||||||
|
for file in files:
|
||||||
|
self.check_file(Path(root) / file)
|
||||||
|
|
||||||
|
print(f"\nGate complete. Failures: {self.failures}, Warnings: {self.warnings}")
|
||||||
|
if self.failures > 0:
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
parser = argparse.ArgumentParser()
|
||||||
|
parser.add_argument("dir", nargs="?", default=".")
|
||||||
|
parser.add_argument("--fix", action="store_true")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
gate = QualityGate(fix=args.fix)
|
||||||
|
gate.run(args.dir)
|
||||||
306
scripts/config_validator.py
Normal file
306
scripts/config_validator.py
Normal file
@@ -0,0 +1,306 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
config_validator.py — Validate all YAML/JSON config files in timmy-config.
|
||||||
|
|
||||||
|
Checks:
|
||||||
|
1. YAML syntax (pyyaml safe_load)
|
||||||
|
2. JSON syntax (json.loads)
|
||||||
|
3. Duplicate keys in YAML/JSON
|
||||||
|
4. Trailing whitespace in YAML
|
||||||
|
5. Tabs in YAML (should use spaces)
|
||||||
|
6. Cron expression validity (if present)
|
||||||
|
|
||||||
|
Exit 0 if all valid, 1 if any invalid.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import json
|
||||||
|
import os
|
||||||
|
import re
|
||||||
|
import sys
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
try:
|
||||||
|
import yaml
|
||||||
|
except ImportError:
|
||||||
|
print("ERROR: PyYAML not installed. Run: pip install pyyaml")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
|
||||||
|
# ── Cron validation ──────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
DOW_NAMES = {"sun", "mon", "tue", "wed", "thu", "fri", "sat"}
|
||||||
|
MONTH_NAMES = {"jan", "feb", "mar", "apr", "may", "jun",
|
||||||
|
"jul", "aug", "sep", "oct", "nov", "dec"}
|
||||||
|
|
||||||
|
|
||||||
|
def _expand_cron_field(field: str, lo: int, hi: int, names: dict | None = None) -> set[int]:
|
||||||
|
"""Expand a single cron field into a set of valid integers."""
|
||||||
|
result: set[int] = set()
|
||||||
|
for part in field.split(","):
|
||||||
|
# Handle step: */N or 1-5/N
|
||||||
|
step = 1
|
||||||
|
if "/" in part:
|
||||||
|
part, step_str = part.split("/", 1)
|
||||||
|
if not step_str.isdigit() or int(step_str) < 1:
|
||||||
|
raise ValueError(f"invalid step value: {step_str}")
|
||||||
|
step = int(step_str)
|
||||||
|
|
||||||
|
if part == "*":
|
||||||
|
rng = range(lo, hi + 1, step)
|
||||||
|
elif "-" in part:
|
||||||
|
a, b = part.split("-", 1)
|
||||||
|
a = _resolve_name(a, names, lo, hi)
|
||||||
|
b = _resolve_name(b, names, lo, hi)
|
||||||
|
if a > b:
|
||||||
|
raise ValueError(f"range {a}-{b} is reversed")
|
||||||
|
rng = range(a, b + 1, step)
|
||||||
|
else:
|
||||||
|
val = _resolve_name(part, names, lo, hi)
|
||||||
|
rng = range(val, val + 1)
|
||||||
|
|
||||||
|
for v in rng:
|
||||||
|
if v < lo or v > hi:
|
||||||
|
raise ValueError(f"value {v} out of range [{lo}-{hi}]")
|
||||||
|
result.add(v)
|
||||||
|
return result
|
||||||
|
|
||||||
|
|
||||||
|
def _resolve_name(token: str, names: dict | None, lo: int, hi: int) -> int:
|
||||||
|
if names and token.lower() in names:
|
||||||
|
return names[token.lower()]
|
||||||
|
if not token.isdigit():
|
||||||
|
raise ValueError(f"unrecognized token: {token}")
|
||||||
|
val = int(token)
|
||||||
|
if val < lo or val > hi:
|
||||||
|
raise ValueError(f"value {val} out of range [{lo}-{hi}]")
|
||||||
|
return val
|
||||||
|
|
||||||
|
|
||||||
|
def validate_cron(expr: str) -> list[str]:
|
||||||
|
"""Validate a 5-field cron expression. Returns list of errors (empty = ok)."""
|
||||||
|
errors: list[str] = []
|
||||||
|
fields = expr.strip().split()
|
||||||
|
if len(fields) != 5:
|
||||||
|
return [f"expected 5 fields, got {len(fields)}"]
|
||||||
|
|
||||||
|
specs = [
|
||||||
|
(fields[0], 0, 59, None, "minute"),
|
||||||
|
(fields[1], 0, 23, None, "hour"),
|
||||||
|
(fields[2], 1, 31, None, "day-of-month"),
|
||||||
|
(fields[3], 1, 12, MONTH_NAMES, "month"),
|
||||||
|
(fields[4], 0, 7, DOW_NAMES, "day-of-week"),
|
||||||
|
]
|
||||||
|
for field, lo, hi, names, label in specs:
|
||||||
|
try:
|
||||||
|
_expand_cron_field(field, lo, hi, names)
|
||||||
|
except ValueError as e:
|
||||||
|
errors.append(f"{label}: {e}")
|
||||||
|
return errors
|
||||||
|
|
||||||
|
|
||||||
|
# ── Duplicate key detection ──────────────────────────────────────────────────
|
||||||
|
|
||||||
|
class DuplicateKeyError(Exception):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
class _StrictYAMLLoader(yaml.SafeLoader):
|
||||||
|
"""YAML loader that rejects duplicate keys."""
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
def _no_duplicates_constructor(loader, node, deep=False):
|
||||||
|
mapping = {}
|
||||||
|
for key_node, value_node in node.value:
|
||||||
|
key = loader.construct_object(key_node, deep=deep)
|
||||||
|
if key in mapping:
|
||||||
|
raise DuplicateKeyError(
|
||||||
|
f"duplicate key '{key}' (line {key_node.start_mark.line + 1})"
|
||||||
|
)
|
||||||
|
mapping[key] = loader.construct_object(value_node, deep=deep)
|
||||||
|
return mapping
|
||||||
|
|
||||||
|
|
||||||
|
_StrictYAMLLoader.add_constructor(
|
||||||
|
yaml.resolver.BaseResolver.DEFAULT_MAPPING_TAG,
|
||||||
|
_no_duplicates_constructor,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _json_has_duplicates(text: str) -> list[str]:
|
||||||
|
"""Check for duplicate keys in JSON by scanning for repeated quoted keys at same depth."""
|
||||||
|
errors: list[str] = []
|
||||||
|
# Use a custom approach: parse with object_pairs_hook
|
||||||
|
seen_stack: list[set[str]] = []
|
||||||
|
|
||||||
|
def _check_pairs(pairs):
|
||||||
|
level_keys: set[str] = set()
|
||||||
|
for k, _ in pairs:
|
||||||
|
if k in level_keys:
|
||||||
|
errors.append(f"duplicate JSON key: '{k}'")
|
||||||
|
level_keys.add(k)
|
||||||
|
return dict(pairs)
|
||||||
|
|
||||||
|
try:
|
||||||
|
json.loads(text, object_pairs_hook=_check_pairs)
|
||||||
|
except json.JSONDecodeError:
|
||||||
|
pass # syntax errors caught elsewhere
|
||||||
|
return errors
|
||||||
|
|
||||||
|
|
||||||
|
# ── Main validator ───────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
def find_config_files(root: Path) -> list[Path]:
|
||||||
|
"""Recursively find .yaml, .yml, .json files (skip .git, node_modules, venv)."""
|
||||||
|
skip_dirs = {".git", "node_modules", "venv", "__pycache__", ".venv"}
|
||||||
|
results: list[Path] = []
|
||||||
|
for dirpath, dirnames, filenames in os.walk(root):
|
||||||
|
dirnames[:] = [d for d in dirnames if d not in skip_dirs]
|
||||||
|
for fname in filenames:
|
||||||
|
if fname.endswith((".yaml", ".yml", ".json")):
|
||||||
|
results.append(Path(dirpath) / fname)
|
||||||
|
return sorted(results)
|
||||||
|
|
||||||
|
|
||||||
|
def validate_yaml_file(filepath: Path, text: str) -> list[str]:
|
||||||
|
"""Validate a YAML file. Returns list of errors."""
|
||||||
|
errors: list[str] = []
|
||||||
|
|
||||||
|
# Check for tabs
|
||||||
|
for i, line in enumerate(text.splitlines(), 1):
|
||||||
|
if "\t" in line:
|
||||||
|
errors.append(f" line {i}: contains tab character (use spaces for YAML)")
|
||||||
|
if line != line.rstrip():
|
||||||
|
errors.append(f" line {i}: trailing whitespace")
|
||||||
|
|
||||||
|
# Check syntax + duplicate keys
|
||||||
|
try:
|
||||||
|
yaml.load(text, Loader=_StrictYAMLLoader)
|
||||||
|
except DuplicateKeyError as e:
|
||||||
|
errors.append(f" {e}")
|
||||||
|
except yaml.YAMLError as e:
|
||||||
|
mark = getattr(e, "problem_mark", None)
|
||||||
|
if mark:
|
||||||
|
errors.append(f" YAML syntax error at line {mark.line + 1}, col {mark.column + 1}: {e.problem}")
|
||||||
|
else:
|
||||||
|
errors.append(f" YAML syntax error: {e}")
|
||||||
|
|
||||||
|
# Check cron expressions in schedule fields
|
||||||
|
for i, line in enumerate(text.splitlines(), 1):
|
||||||
|
cron_match = re.search(r'(?:cron|schedule)\s*:\s*["\']?([*0-9/,a-zA-Z-]+(?:\s+[*0-9/,a-zA-Z-]+){4})["\']?', line)
|
||||||
|
if cron_match:
|
||||||
|
cron_errs = validate_cron(cron_match.group(1))
|
||||||
|
for ce in cron_errs:
|
||||||
|
errors.append(f" line {i}: invalid cron '{cron_match.group(1)}': {ce}")
|
||||||
|
|
||||||
|
return errors
|
||||||
|
|
||||||
|
|
||||||
|
def validate_json_file(filepath: Path, text: str) -> list[str]:
|
||||||
|
"""Validate a JSON file. Returns list of errors."""
|
||||||
|
errors: list[str] = []
|
||||||
|
|
||||||
|
# Check syntax
|
||||||
|
try:
|
||||||
|
json.loads(text)
|
||||||
|
except json.JSONDecodeError as e:
|
||||||
|
errors.append(f" JSON syntax error at line {e.lineno}, col {e.colno}: {e.msg}")
|
||||||
|
|
||||||
|
# Check duplicate keys
|
||||||
|
dup_errors = _json_has_duplicates(text)
|
||||||
|
errors.extend(dup_errors)
|
||||||
|
|
||||||
|
# Check for trailing whitespace (informational)
|
||||||
|
for i, line in enumerate(text.splitlines(), 1):
|
||||||
|
if line != line.rstrip():
|
||||||
|
errors.append(f" line {i}: trailing whitespace")
|
||||||
|
|
||||||
|
# Check cron expressions
|
||||||
|
cron_pattern = re.compile(r'"(?:cron|schedule)"?\s*:\s*"([^"]{5,})"')
|
||||||
|
for match in cron_pattern.finditer(text):
|
||||||
|
candidate = match.group(1).strip()
|
||||||
|
fields = candidate.split()
|
||||||
|
if len(fields) == 5 and all(re.match(r'^[*0-9/,a-zA-Z-]+$', f) for f in fields):
|
||||||
|
cron_errs = validate_cron(candidate)
|
||||||
|
for ce in cron_errs:
|
||||||
|
errors.append(f" invalid cron '{candidate}': {ce}")
|
||||||
|
|
||||||
|
# Also check nested schedule objects with cron fields
|
||||||
|
try:
|
||||||
|
obj = json.loads(text)
|
||||||
|
_scan_obj_for_cron(obj, errors)
|
||||||
|
except Exception:
|
||||||
|
pass
|
||||||
|
|
||||||
|
return errors
|
||||||
|
|
||||||
|
|
||||||
|
def _scan_obj_for_cron(obj, errors: list[str], path: str = ""):
|
||||||
|
"""Recursively scan dict/list for cron expressions."""
|
||||||
|
if isinstance(obj, dict):
|
||||||
|
for k, v in obj.items():
|
||||||
|
if k in ("cron", "schedule", "cron_expression") and isinstance(v, str):
|
||||||
|
fields = v.strip().split()
|
||||||
|
if len(fields) == 5:
|
||||||
|
cron_errs = validate_cron(v)
|
||||||
|
for ce in cron_errs:
|
||||||
|
errors.append(f" {path}.{k}: invalid cron '{v}': {ce}")
|
||||||
|
_scan_obj_for_cron(v, errors, f"{path}.{k}")
|
||||||
|
elif isinstance(obj, list):
|
||||||
|
for i, item in enumerate(obj):
|
||||||
|
_scan_obj_for_cron(item, errors, f"{path}[{i}]")
|
||||||
|
|
||||||
|
|
||||||
|
def main():
|
||||||
|
# Determine repo root (script lives in scripts/)
|
||||||
|
script_path = Path(__file__).resolve()
|
||||||
|
repo_root = script_path.parent.parent
|
||||||
|
|
||||||
|
print(f"Config Validator — scanning {repo_root}")
|
||||||
|
print("=" * 60)
|
||||||
|
|
||||||
|
files = find_config_files(repo_root)
|
||||||
|
print(f"Found {len(files)} config files to validate.\n")
|
||||||
|
|
||||||
|
total_errors = 0
|
||||||
|
failed_files: list[tuple[Path, list[str]]] = []
|
||||||
|
|
||||||
|
for filepath in files:
|
||||||
|
rel = filepath.relative_to(repo_root)
|
||||||
|
try:
|
||||||
|
text = filepath.read_text(encoding="utf-8", errors="replace")
|
||||||
|
except Exception as e:
|
||||||
|
failed_files.append((rel, [f" cannot read file: {e}"]))
|
||||||
|
total_errors += 1
|
||||||
|
continue
|
||||||
|
|
||||||
|
if filepath.suffix == ".json":
|
||||||
|
errors = validate_json_file(filepath, text)
|
||||||
|
else:
|
||||||
|
errors = validate_yaml_file(filepath, text)
|
||||||
|
|
||||||
|
if errors:
|
||||||
|
failed_files.append((rel, errors))
|
||||||
|
total_errors += len(errors)
|
||||||
|
print(f"FAIL {rel}")
|
||||||
|
else:
|
||||||
|
print(f"PASS {rel}")
|
||||||
|
|
||||||
|
print("\n" + "=" * 60)
|
||||||
|
print(f"Results: {len(files) - len(failed_files)}/{len(files)} files passed")
|
||||||
|
|
||||||
|
if failed_files:
|
||||||
|
print(f"\n{total_errors} error(s) in {len(failed_files)} file(s):\n")
|
||||||
|
for relpath, errs in failed_files:
|
||||||
|
print(f" {relpath}:")
|
||||||
|
for e in errs:
|
||||||
|
print(f" {e}")
|
||||||
|
print()
|
||||||
|
sys.exit(1)
|
||||||
|
else:
|
||||||
|
print("\nAll config files valid!")
|
||||||
|
sys.exit(0)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
90
scripts/cross_repo_test.py
Normal file
90
scripts/cross_repo_test.py
Normal file
@@ -0,0 +1,90 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[OPS] Cross-Repo Test Suite
|
||||||
|
Part of the Gemini Sovereign Infrastructure Suite.
|
||||||
|
|
||||||
|
Verifies the fleet works as a system by running tests across all core repositories.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import subprocess
|
||||||
|
import argparse
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
# --- CONFIGURATION ---
|
||||||
|
REPOS = ["timmy-config", "hermes-agent", "the-nexus"]
|
||||||
|
|
||||||
|
class CrossRepoTester:
|
||||||
|
def __init__(self, root_dir: str):
|
||||||
|
self.root_dir = Path(root_dir).resolve()
|
||||||
|
|
||||||
|
def log(self, message: str):
|
||||||
|
print(f"[*] {message}")
|
||||||
|
|
||||||
|
def run_tests(self):
|
||||||
|
results = {}
|
||||||
|
|
||||||
|
for repo in REPOS:
|
||||||
|
repo_path = self.root_dir / repo
|
||||||
|
if not repo_path.exists():
|
||||||
|
# Try sibling directory if we are in one of the repos
|
||||||
|
repo_path = self.root_dir.parent / repo
|
||||||
|
|
||||||
|
if not repo_path.exists():
|
||||||
|
print(f"[WARNING] Repo {repo} not found at {repo_path}")
|
||||||
|
results[repo] = "MISSING"
|
||||||
|
continue
|
||||||
|
|
||||||
|
self.log(f"Running tests for {repo}...")
|
||||||
|
|
||||||
|
# Determine test command
|
||||||
|
test_cmd = ["pytest"]
|
||||||
|
if repo == "hermes-agent":
|
||||||
|
test_cmd = ["python3", "-m", "pytest", "tests"]
|
||||||
|
elif repo == "the-nexus":
|
||||||
|
test_cmd = ["pytest", "tests"]
|
||||||
|
|
||||||
|
try:
|
||||||
|
# Check if pytest is available
|
||||||
|
subprocess.run(["pytest", "--version"], capture_output=True)
|
||||||
|
|
||||||
|
res = subprocess.run(test_cmd, cwd=str(repo_path), capture_output=True, text=True)
|
||||||
|
if res.returncode == 0:
|
||||||
|
results[repo] = "PASSED"
|
||||||
|
else:
|
||||||
|
results[repo] = "FAILED"
|
||||||
|
# Print a snippet of the failure
|
||||||
|
print(f" [!] {repo} failed tests. Stderr snippet:")
|
||||||
|
print("\n".join(res.stderr.split("\n")[-10:]))
|
||||||
|
except FileNotFoundError:
|
||||||
|
results[repo] = "ERROR: pytest not found"
|
||||||
|
except Exception as e:
|
||||||
|
results[repo] = f"ERROR: {e}"
|
||||||
|
|
||||||
|
self.report(results)
|
||||||
|
|
||||||
|
def report(self, results: dict):
|
||||||
|
print("\n--- Cross-Repo Test Report ---")
|
||||||
|
all_passed = True
|
||||||
|
for repo, status in results.items():
|
||||||
|
icon = "✅" if status == "PASSED" else "❌"
|
||||||
|
print(f"{icon} {repo:<15} | {status}")
|
||||||
|
if status != "PASSED":
|
||||||
|
all_passed = False
|
||||||
|
|
||||||
|
if all_passed:
|
||||||
|
print("\n[SUCCESS] All systems operational. The fleet is sound.")
|
||||||
|
else:
|
||||||
|
print("\n[FAILURE] System instability detected.")
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Gemini Cross-Repo Tester")
|
||||||
|
parser.add_argument("--root", default=".", help="Root directory containing all repos")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
tester = CrossRepoTester(args.root)
|
||||||
|
tester.run_tests()
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
11
scripts/diagram_meaning_extractor.py
Normal file
11
scripts/diagram_meaning_extractor.py
Normal file
@@ -0,0 +1,11 @@
|
|||||||
|
import json
|
||||||
|
from hermes_tools import browser_navigate, browser_vision
|
||||||
|
|
||||||
|
def extract_meaning():
|
||||||
|
analysis = browser_vision(
|
||||||
|
question="Analyze the provided diagram. Extract the core logic flow and map it to a 'Meaning Kernel' (entity -> relationship -> entity). Provide output in JSON."
|
||||||
|
)
|
||||||
|
return {"analysis": analysis}
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
print(json.dumps(extract_meaning(), indent=2))
|
||||||
390
scripts/fleet-dashboard.py
Executable file
390
scripts/fleet-dashboard.py
Executable file
@@ -0,0 +1,390 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
fleet-dashboard.py -- Timmy Foundation Fleet Status Dashboard.
|
||||||
|
|
||||||
|
One-page terminal dashboard showing:
|
||||||
|
1. Gitea: open PRs, open issues, recent merges
|
||||||
|
2. VPS health: SSH reachability, service status, disk usage
|
||||||
|
3. Cron jobs: scheduled jobs, last run status
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
python3 scripts/fleet-dashboard.py
|
||||||
|
python3 scripts/fleet-dashboard.py --json # machine-readable output
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import json
|
||||||
|
import os
|
||||||
|
import socket
|
||||||
|
import subprocess
|
||||||
|
import sys
|
||||||
|
import time
|
||||||
|
import urllib.request
|
||||||
|
import urllib.error
|
||||||
|
from datetime import datetime, timezone, timedelta
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Config
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
GITEA_BASE = os.environ.get("GITEA_URL", "https://forge.alexanderwhitestone.com")
|
||||||
|
GITEA_API = f"{GITEA_BASE}/api/v1"
|
||||||
|
GITEA_ORG = "Timmy_Foundation"
|
||||||
|
|
||||||
|
# Key repos to check for PRs/issues
|
||||||
|
REPOS = [
|
||||||
|
"timmy-config",
|
||||||
|
"the-nexus",
|
||||||
|
"hermes-agent",
|
||||||
|
"the-forge",
|
||||||
|
"timmy-sandbox",
|
||||||
|
]
|
||||||
|
|
||||||
|
# VPS fleet
|
||||||
|
VPS_HOSTS = {
|
||||||
|
"ezra": {
|
||||||
|
"ip": "143.198.27.163",
|
||||||
|
"ssh_user": "root",
|
||||||
|
"services": ["nginx", "gitea", "docker"],
|
||||||
|
},
|
||||||
|
"allegro": {
|
||||||
|
"ip": "167.99.126.228",
|
||||||
|
"ssh_user": "root",
|
||||||
|
"services": ["hermes-agent"],
|
||||||
|
},
|
||||||
|
"bezalel": {
|
||||||
|
"ip": "159.203.146.185",
|
||||||
|
"ssh_user": "root",
|
||||||
|
"services": ["hermes-agent", "evennia"],
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
CRON_JOBS_FILE = Path(__file__).parent.parent / "cron" / "jobs.json"
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Gitea helpers
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
def _gitea_token() -> str:
|
||||||
|
for p in [
|
||||||
|
Path.home() / ".hermes" / "gitea_token",
|
||||||
|
Path.home() / ".hermes" / "gitea_token_vps",
|
||||||
|
Path.home() / ".config" / "gitea" / "token",
|
||||||
|
]:
|
||||||
|
if p.exists():
|
||||||
|
return p.read_text().strip()
|
||||||
|
return ""
|
||||||
|
|
||||||
|
|
||||||
|
def _gitea_get(path: str, params: dict | None = None) -> list | dict:
|
||||||
|
url = f"{GITEA_API}{path}"
|
||||||
|
if params:
|
||||||
|
qs = "&".join(f"{k}={v}" for k, v in params.items() if v is not None)
|
||||||
|
if qs:
|
||||||
|
url += f"?{qs}"
|
||||||
|
req = urllib.request.Request(url)
|
||||||
|
token = _gitea_token()
|
||||||
|
if token:
|
||||||
|
req.add_header("Authorization", f"token {token}")
|
||||||
|
req.add_header("Accept", "application/json")
|
||||||
|
try:
|
||||||
|
with urllib.request.urlopen(req, timeout=15) as resp:
|
||||||
|
return json.loads(resp.read())
|
||||||
|
except Exception as e:
|
||||||
|
return {"error": str(e)}
|
||||||
|
|
||||||
|
|
||||||
|
def check_gitea_health() -> dict:
|
||||||
|
"""Ping Gitea and collect PR/issue stats."""
|
||||||
|
result = {"reachable": False, "version": "", "repos": {}, "totals": {}}
|
||||||
|
|
||||||
|
# Ping
|
||||||
|
data = _gitea_get("/version")
|
||||||
|
if isinstance(data, dict) and "error" not in data:
|
||||||
|
result["reachable"] = True
|
||||||
|
result["version"] = data.get("version", "unknown")
|
||||||
|
elif isinstance(data, dict) and "error" in data:
|
||||||
|
return result
|
||||||
|
|
||||||
|
total_open_prs = 0
|
||||||
|
total_open_issues = 0
|
||||||
|
total_recent_merges = 0
|
||||||
|
cutoff = (datetime.now(timezone.utc) - timedelta(days=7)).strftime("%Y-%m-%dT%H:%M:%SZ")
|
||||||
|
|
||||||
|
for repo in REPOS:
|
||||||
|
repo_path = f"/repos/{GITEA_ORG}/{repo}"
|
||||||
|
repo_info = {"prs": [], "issues": [], "recent_merges": 0}
|
||||||
|
|
||||||
|
# Open PRs
|
||||||
|
prs = _gitea_get(f"{repo_path}/pulls", {"state": "open", "limit": "10", "sort": "newest"})
|
||||||
|
if isinstance(prs, list):
|
||||||
|
for pr in prs:
|
||||||
|
repo_info["prs"].append({
|
||||||
|
"number": pr.get("number"),
|
||||||
|
"title": pr.get("title", "")[:60],
|
||||||
|
"user": pr.get("user", {}).get("login", "unknown"),
|
||||||
|
"created": pr.get("created_at", "")[:10],
|
||||||
|
})
|
||||||
|
total_open_prs += len(prs)
|
||||||
|
|
||||||
|
# Open issues (excluding PRs)
|
||||||
|
issues = _gitea_get(f"{repo_path}/issues", {
|
||||||
|
"state": "open", "type": "issues", "limit": "10", "sort": "newest"
|
||||||
|
})
|
||||||
|
if isinstance(issues, list):
|
||||||
|
for iss in issues:
|
||||||
|
repo_info["issues"].append({
|
||||||
|
"number": iss.get("number"),
|
||||||
|
"title": iss.get("title", "")[:60],
|
||||||
|
"user": iss.get("user", {}).get("login", "unknown"),
|
||||||
|
"created": iss.get("created_at", "")[:10],
|
||||||
|
})
|
||||||
|
total_open_issues += len(issues)
|
||||||
|
|
||||||
|
# Recent merges (closed PRs)
|
||||||
|
merged = _gitea_get(f"{repo_path}/pulls", {"state": "closed", "limit": "20", "sort": "newest"})
|
||||||
|
if isinstance(merged, list):
|
||||||
|
recent = [p for p in merged if p.get("merged") and p.get("closed_at", "") >= cutoff]
|
||||||
|
repo_info["recent_merges"] = len(recent)
|
||||||
|
total_recent_merges += len(recent)
|
||||||
|
|
||||||
|
result["repos"][repo] = repo_info
|
||||||
|
|
||||||
|
result["totals"] = {
|
||||||
|
"open_prs": total_open_prs,
|
||||||
|
"open_issues": total_open_issues,
|
||||||
|
"recent_merges_7d": total_recent_merges,
|
||||||
|
}
|
||||||
|
return result
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# VPS health helpers
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
def check_ssh(ip: str, timeout: int = 5) -> bool:
|
||||||
|
try:
|
||||||
|
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
||||||
|
sock.settimeout(timeout)
|
||||||
|
result = sock.connect_ex((ip, 22))
|
||||||
|
sock.close()
|
||||||
|
return result == 0
|
||||||
|
except Exception:
|
||||||
|
return False
|
||||||
|
|
||||||
|
|
||||||
|
def check_service(ip: str, user: str, service: str) -> str:
|
||||||
|
"""Check if a systemd service is active on remote host."""
|
||||||
|
cmd = f"ssh -o StrictHostKeyChecking=no -o ConnectTimeout=8 {user}@{ip} 'systemctl is-active {service} 2>/dev/null || echo inactive'"
|
||||||
|
try:
|
||||||
|
proc = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=15)
|
||||||
|
return proc.stdout.strip() or "unknown"
|
||||||
|
except subprocess.TimeoutExpired:
|
||||||
|
return "timeout"
|
||||||
|
except Exception:
|
||||||
|
return "error"
|
||||||
|
|
||||||
|
|
||||||
|
def check_disk(ip: str, user: str) -> dict:
|
||||||
|
cmd = f"ssh -o StrictHostKeyChecking=no -o ConnectTimeout=8 {user}@{ip} 'df -h / | tail -1'"
|
||||||
|
try:
|
||||||
|
proc = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=15)
|
||||||
|
if proc.returncode == 0:
|
||||||
|
parts = proc.stdout.strip().split()
|
||||||
|
if len(parts) >= 5:
|
||||||
|
return {"total": parts[1], "used": parts[2], "avail": parts[3], "pct": parts[4]}
|
||||||
|
except Exception:
|
||||||
|
pass
|
||||||
|
return {"total": "?", "used": "?", "avail": "?", "pct": "?"}
|
||||||
|
|
||||||
|
|
||||||
|
def check_vps_health() -> dict:
|
||||||
|
result = {}
|
||||||
|
for name, cfg in VPS_HOSTS.items():
|
||||||
|
ip = cfg["ip"]
|
||||||
|
ssh_up = check_ssh(ip)
|
||||||
|
entry = {"ip": ip, "ssh": ssh_up, "services": {}, "disk": {}}
|
||||||
|
if ssh_up:
|
||||||
|
for svc in cfg.get("services", []):
|
||||||
|
entry["services"][svc] = check_service(ip, cfg["ssh_user"], svc)
|
||||||
|
entry["disk"] = check_disk(ip, cfg["ssh_user"])
|
||||||
|
result[name] = entry
|
||||||
|
return result
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Cron job status
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
def check_cron_jobs() -> list[dict]:
|
||||||
|
jobs = []
|
||||||
|
if not CRON_JOBS_FILE.exists():
|
||||||
|
return [{"name": "jobs.json", "status": "FILE NOT FOUND"}]
|
||||||
|
try:
|
||||||
|
data = json.loads(CRON_JOBS_FILE.read_text())
|
||||||
|
for job in data.get("jobs", []):
|
||||||
|
jobs.append({
|
||||||
|
"name": job.get("name", "unnamed"),
|
||||||
|
"schedule": job.get("schedule_display", job.get("schedule", {}).get("display", "?")),
|
||||||
|
"enabled": job.get("enabled", False),
|
||||||
|
"state": job.get("state", "unknown"),
|
||||||
|
"completed": job.get("repeat", {}).get("completed", 0),
|
||||||
|
"last_status": job.get("last_status") or "never run",
|
||||||
|
"last_error": job.get("last_error"),
|
||||||
|
})
|
||||||
|
except Exception as e:
|
||||||
|
jobs.append({"name": "jobs.json", "status": f"PARSE ERROR: {e}"})
|
||||||
|
return jobs
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Terminal rendering
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
BOLD = "\033[1m"
|
||||||
|
DIM = "\033[2m"
|
||||||
|
GREEN = "\033[32m"
|
||||||
|
RED = "\033[31m"
|
||||||
|
YELLOW = "\033[33m"
|
||||||
|
CYAN = "\033[36m"
|
||||||
|
RESET = "\033[0m"
|
||||||
|
|
||||||
|
|
||||||
|
def _ok(val: bool) -> str:
|
||||||
|
return f"{GREEN}UP{RESET}" if val else f"{RED}DOWN{RESET}"
|
||||||
|
|
||||||
|
|
||||||
|
def _svc_icon(status: str) -> str:
|
||||||
|
s = status.lower().strip()
|
||||||
|
if s in ("active", "running"):
|
||||||
|
return f"{GREEN}active{RESET}"
|
||||||
|
elif s in ("inactive", "dead", "failed"):
|
||||||
|
return f"{RED}{s}{RESET}"
|
||||||
|
elif s == "timeout":
|
||||||
|
return f"{YELLOW}timeout{RESET}"
|
||||||
|
else:
|
||||||
|
return f"{YELLOW}{s}{RESET}"
|
||||||
|
|
||||||
|
|
||||||
|
def render_dashboard(gitea: dict, vps: dict, cron: list[dict]) -> str:
|
||||||
|
lines = []
|
||||||
|
now = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
|
||||||
|
lines.append("")
|
||||||
|
lines.append(f"{BOLD}{'=' * 72}{RESET}")
|
||||||
|
lines.append(f"{BOLD} TIMMY FOUNDATION -- FLEET STATUS DASHBOARD{RESET}")
|
||||||
|
lines.append(f"{DIM} Generated: {now}{RESET}")
|
||||||
|
lines.append(f"{BOLD}{'=' * 72}{RESET}")
|
||||||
|
|
||||||
|
# ── Section 1: Gitea ──────────────────────────────────────────────────
|
||||||
|
lines.append("")
|
||||||
|
lines.append(f"{BOLD}{CYAN} [1] GITEA{RESET}")
|
||||||
|
lines.append(f" {'-' * 68}")
|
||||||
|
if gitea.get("reachable"):
|
||||||
|
lines.append(f" Status: {GREEN}REACHABLE{RESET} (version {gitea.get('version', '?')})")
|
||||||
|
t = gitea.get("totals", {})
|
||||||
|
lines.append(f" Totals: {t.get('open_prs', 0)} open PRs | {t.get('open_issues', 0)} open issues | {t.get('recent_merges_7d', 0)} merges (7d)")
|
||||||
|
lines.append("")
|
||||||
|
for repo_name, repo in gitea.get("repos", {}).items():
|
||||||
|
prs = repo.get("prs", [])
|
||||||
|
issues = repo.get("issues", [])
|
||||||
|
merges = repo.get("recent_merges", 0)
|
||||||
|
lines.append(f" {BOLD}{repo_name}{RESET} ({len(prs)} PRs, {len(issues)} issues, {merges} merges/7d)")
|
||||||
|
for pr in prs[:5]:
|
||||||
|
lines.append(f" PR #{pr['number']:>4} {pr['title'][:50]:<50} {DIM}{pr['user']}{RESET} {pr['created']}")
|
||||||
|
for iss in issues[:3]:
|
||||||
|
lines.append(f" IS #{iss['number']:>4} {iss['title'][:50]:<50} {DIM}{iss['user']}{RESET} {iss['created']}")
|
||||||
|
else:
|
||||||
|
lines.append(f" Status: {RED}UNREACHABLE{RESET}")
|
||||||
|
|
||||||
|
# ── Section 2: VPS Health ─────────────────────────────────────────────
|
||||||
|
lines.append("")
|
||||||
|
lines.append(f"{BOLD}{CYAN} [2] VPS HEALTH{RESET}")
|
||||||
|
lines.append(f" {'-' * 68}")
|
||||||
|
lines.append(f" {'Host':<12} {'IP':<18} {'SSH':<8} {'Disk':<12} {'Services'}")
|
||||||
|
lines.append(f" {'-' * 12} {'-' * 17} {'-' * 7} {'-' * 11} {'-' * 30}")
|
||||||
|
for name, info in vps.items():
|
||||||
|
ssh_str = _ok(info["ssh"])
|
||||||
|
disk = info.get("disk", {})
|
||||||
|
disk_str = disk.get("pct", "?")
|
||||||
|
if disk_str != "?":
|
||||||
|
pct_val = int(disk_str.rstrip("%"))
|
||||||
|
if pct_val >= 90:
|
||||||
|
disk_str = f"{RED}{disk_str}{RESET}"
|
||||||
|
elif pct_val >= 75:
|
||||||
|
disk_str = f"{YELLOW}{disk_str}{RESET}"
|
||||||
|
else:
|
||||||
|
disk_str = f"{GREEN}{disk_str}{RESET}"
|
||||||
|
svc_parts = []
|
||||||
|
for svc, status in info.get("services", {}).items():
|
||||||
|
svc_parts.append(f"{svc}:{_svc_icon(status)}")
|
||||||
|
svc_str = " ".join(svc_parts) if svc_parts else f"{DIM}n/a{RESET}"
|
||||||
|
lines.append(f" {name:<12} {info['ip']:<18} {ssh_str:<18} {disk_str:<22} {svc_str}")
|
||||||
|
|
||||||
|
# ── Section 3: Cron Jobs ──────────────────────────────────────────────
|
||||||
|
lines.append("")
|
||||||
|
lines.append(f"{BOLD}{CYAN} [3] CRON JOBS{RESET}")
|
||||||
|
lines.append(f" {'-' * 68}")
|
||||||
|
lines.append(f" {'Name':<28} {'Schedule':<16} {'State':<12} {'Last':<12} {'Runs'}")
|
||||||
|
lines.append(f" {'-' * 27} {'-' * 15} {'-' * 11} {'-' * 11} {'-' * 5}")
|
||||||
|
for job in cron:
|
||||||
|
name = job.get("name", "?")[:27]
|
||||||
|
sched = job.get("schedule", "?")[:15]
|
||||||
|
state = job.get("state", "?")
|
||||||
|
if state == "scheduled":
|
||||||
|
state_str = f"{GREEN}{state}{RESET}"
|
||||||
|
elif state == "paused":
|
||||||
|
state_str = f"{YELLOW}{state}{RESET}"
|
||||||
|
else:
|
||||||
|
state_str = state
|
||||||
|
last = job.get("last_status", "never")[:11]
|
||||||
|
if last == "ok":
|
||||||
|
last_str = f"{GREEN}{last}{RESET}"
|
||||||
|
elif last in ("error", "never run"):
|
||||||
|
last_str = f"{RED}{last}{RESET}"
|
||||||
|
else:
|
||||||
|
last_str = last
|
||||||
|
runs = job.get("completed", 0)
|
||||||
|
enabled = job.get("enabled", False)
|
||||||
|
marker = " " if enabled else f"{DIM}(disabled){RESET}"
|
||||||
|
lines.append(f" {name:<28} {sched:<16} {state_str:<22} {last_str:<22} {runs} {marker}")
|
||||||
|
|
||||||
|
# ── Footer ────────────────────────────────────────────────────────────
|
||||||
|
lines.append("")
|
||||||
|
lines.append(f"{BOLD}{'=' * 72}{RESET}")
|
||||||
|
lines.append(f"{DIM} python3 scripts/fleet-dashboard.py | timmy-config{RESET}")
|
||||||
|
lines.append(f"{BOLD}{'=' * 72}{RESET}")
|
||||||
|
lines.append("")
|
||||||
|
|
||||||
|
return "\n".join(lines)
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Main
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
def main():
|
||||||
|
json_mode = "--json" in sys.argv
|
||||||
|
|
||||||
|
if not json_mode:
|
||||||
|
print(f"\n {DIM}Collecting fleet data...{RESET}\n", file=sys.stderr)
|
||||||
|
|
||||||
|
gitea = check_gitea_health()
|
||||||
|
vps = check_vps_health()
|
||||||
|
cron = check_cron_jobs()
|
||||||
|
|
||||||
|
if json_mode:
|
||||||
|
output = {
|
||||||
|
"timestamp": datetime.now(timezone.utc).isoformat(),
|
||||||
|
"gitea": gitea,
|
||||||
|
"vps": vps,
|
||||||
|
"cron": cron,
|
||||||
|
}
|
||||||
|
print(json.dumps(output, indent=2))
|
||||||
|
else:
|
||||||
|
print(render_dashboard(gitea, vps, cron))
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
143
scripts/fleet_llama.py
Normal file
143
scripts/fleet_llama.py
Normal file
@@ -0,0 +1,143 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[OPS] llama.cpp Fleet Manager
|
||||||
|
Part of the Gemini Sovereign Infrastructure Suite.
|
||||||
|
|
||||||
|
Manages llama-server instances across the Timmy Foundation fleet.
|
||||||
|
Supports status, restart, and model swapping via SSH.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import json
|
||||||
|
import argparse
|
||||||
|
import requests
|
||||||
|
from typing import Dict, List, Any
|
||||||
|
|
||||||
|
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||||
|
if SCRIPT_DIR not in sys.path:
|
||||||
|
sys.path.insert(0, SCRIPT_DIR)
|
||||||
|
|
||||||
|
from ssh_trust import VerifiedSSHExecutor
|
||||||
|
|
||||||
|
# --- FLEET DEFINITION ---
|
||||||
|
FLEET = {
|
||||||
|
"mac": {"ip": "10.1.10.77", "port": 8080, "role": "hub"},
|
||||||
|
"ezra": {"ip": "143.198.27.163", "port": 8080, "role": "forge"},
|
||||||
|
"allegro": {"ip": "167.99.126.228", "port": 8080, "role": "agent-host"},
|
||||||
|
"bezalel": {"ip": "159.203.146.185", "port": 8080, "role": "world-host"}
|
||||||
|
}
|
||||||
|
|
||||||
|
class FleetManager:
|
||||||
|
def __init__(self, executor=None):
|
||||||
|
self.results = {}
|
||||||
|
self.executor = executor or VerifiedSSHExecutor()
|
||||||
|
|
||||||
|
def run_remote(self, host: str, command: str):
|
||||||
|
ip = FLEET[host]["ip"]
|
||||||
|
ssh_cmd = [
|
||||||
|
"ssh", "-o", "StrictHostKeyChecking=no", "-o", "ConnectTimeout=5",
|
||||||
|
f"root@{ip}", command
|
||||||
|
]
|
||||||
|
# For Mac, we might need a different user or local execution
|
||||||
|
if host == "mac":
|
||||||
|
ssh_cmd = ["bash", "-c", command]
|
||||||
|
|
||||||
|
try:
|
||||||
|
result = subprocess.run(ssh_cmd, capture_output=True, text=True, timeout=10)
|
||||||
|
return result
|
||||||
|
except subprocess.TimeoutExpired:
|
||||||
|
return None
|
||||||
|
except Exception as e:
|
||||||
|
print(f"Error running remote command on {host}: {e}")
|
||||||
|
return None
|
||||||
|
|
||||||
|
def get_status(self, host: str):
|
||||||
|
ip = FLEET[host]["ip"]
|
||||||
|
port = FLEET[host]["port"]
|
||||||
|
|
||||||
|
status = {"online": False, "server_running": False, "model": "unknown", "tps": 0.0}
|
||||||
|
|
||||||
|
# 1. Check if machine is reachable
|
||||||
|
ping_res = subprocess.run(["ping", "-c", "1", "-W", "1", ip], capture_output=True)
|
||||||
|
if ping_res.returncode == 0:
|
||||||
|
status["online"] = True
|
||||||
|
|
||||||
|
# 2. Check if llama-server is responding to health check
|
||||||
|
try:
|
||||||
|
url = f"http://{ip}:{port}/health"
|
||||||
|
response = requests.get(url, timeout=2)
|
||||||
|
if response.status_code == 200:
|
||||||
|
status["server_running"] = True
|
||||||
|
data = response.json()
|
||||||
|
# llama.cpp health endpoint usually returns slots info
|
||||||
|
# We'll try to get model info if available
|
||||||
|
status["model"] = data.get("model", "unknown")
|
||||||
|
except:
|
||||||
|
pass
|
||||||
|
|
||||||
|
return status
|
||||||
|
|
||||||
|
def show_fleet_status(self):
|
||||||
|
print(f"{'NAME':<10} {'IP':<15} {'STATUS':<10} {'SERVER':<10} {'MODEL':<20}")
|
||||||
|
print("-" * 70)
|
||||||
|
for name in FLEET:
|
||||||
|
status = self.get_status(name)
|
||||||
|
online_str = "✅" if status["online"] else "❌"
|
||||||
|
server_str = "🚀" if status["server_running"] else "💤"
|
||||||
|
print(f"{name:<10} {FLEET[name]['ip']:<15} {online_str:<10} {server_str:<10} {status['model']:<20}")
|
||||||
|
|
||||||
|
def restart_server(self, host: str):
|
||||||
|
print(f"[*] Restarting llama-server on {host}...")
|
||||||
|
res = self.run_remote(host, "systemctl restart llama-server")
|
||||||
|
if res and res.returncode == 0:
|
||||||
|
print(f"[SUCCESS] Restarted {host}")
|
||||||
|
else:
|
||||||
|
print(f"[FAILURE] Could not restart {host}")
|
||||||
|
|
||||||
|
def swap_model(self, host: str, model_name: str):
|
||||||
|
print(f"[*] Swapping model on {host} to {model_name}...")
|
||||||
|
# This assumes the provision_wizard.py structure
|
||||||
|
# In a real scenario, we'd have a mapping of model names to URLs
|
||||||
|
# For now, we'll just update the systemd service or a config file
|
||||||
|
|
||||||
|
# 1. Stop server
|
||||||
|
self.run_remote(host, "systemctl stop llama-server")
|
||||||
|
|
||||||
|
# 2. Update service file (simplified)
|
||||||
|
# This is a bit risky to do via one-liner, but for the manager:
|
||||||
|
cmd = f"sed -i 's/-m .*\\.gguf/-m \\/opt\\/models\\/{model_name}.gguf/' /etc/systemd/system/llama-server.service"
|
||||||
|
self.run_remote(host, cmd)
|
||||||
|
|
||||||
|
# 3. Start server
|
||||||
|
self.run_remote(host, "systemctl daemon-reload && systemctl start llama-server")
|
||||||
|
print(f"[SUCCESS] Swapped model on {host}")
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Gemini Fleet Manager")
|
||||||
|
subparsers = parser.add_subparsers(dest="command")
|
||||||
|
|
||||||
|
subparsers.add_parser("status", help="Show fleet status")
|
||||||
|
|
||||||
|
restart_parser = subparsers.add_parser("restart", help="Restart a server")
|
||||||
|
restart_parser.add_argument("host", choices=list(FLEET.keys()), help="Host to restart")
|
||||||
|
|
||||||
|
swap_parser = subparsers.add_parser("swap", help="Swap model on a host")
|
||||||
|
swap_parser.add_argument("host", choices=list(FLEET.keys()), help="Host to swap")
|
||||||
|
swap_parser.add_argument("model", help="Model name (GGUF)")
|
||||||
|
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
manager = FleetManager()
|
||||||
|
|
||||||
|
if args.command == "status":
|
||||||
|
manager.show_fleet_status()
|
||||||
|
elif args.command == "restart":
|
||||||
|
manager.restart_server(args.host)
|
||||||
|
elif args.command == "swap":
|
||||||
|
manager.swap_model(args.host, args.model)
|
||||||
|
else:
|
||||||
|
parser.print_help()
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
12
scripts/foundation_accessibility_audit.py
Normal file
12
scripts/foundation_accessibility_audit.py
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
import json
|
||||||
|
from hermes_tools import browser_navigate, browser_vision
|
||||||
|
|
||||||
|
def audit_accessibility():
|
||||||
|
browser_navigate(url="https://timmyfoundation.org")
|
||||||
|
analysis = browser_vision(
|
||||||
|
question="Perform an accessibility audit. Check for: 1) Color contrast, 2) Font legibility, 3) Missing alt text for images. Provide a report with FAIL/PASS."
|
||||||
|
)
|
||||||
|
return {"status": "PASS" if "PASS" in analysis.upper() else "FAIL", "analysis": analysis}
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
print(json.dumps(audit_accessibility(), indent=2))
|
||||||
82
scripts/gitea_webhook_handler.py
Normal file
82
scripts/gitea_webhook_handler.py
Normal file
@@ -0,0 +1,82 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[OPS] Gitea Webhook Handler
|
||||||
|
Part of the Gemini Sovereign Infrastructure Suite.
|
||||||
|
|
||||||
|
Handles real-time events from Gitea to coordinate fleet actions.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import json
|
||||||
|
import argparse
|
||||||
|
from typing import Dict, Any
|
||||||
|
|
||||||
|
class WebhookHandler:
|
||||||
|
def handle_event(self, payload: Dict[str, Any]):
|
||||||
|
# Gitea webhooks often send the event type in a header,
|
||||||
|
# but we'll try to infer it from the payload if not provided.
|
||||||
|
event_type = payload.get("event") or self.infer_event_type(payload)
|
||||||
|
repo_name = payload.get("repository", {}).get("name")
|
||||||
|
sender = payload.get("sender", {}).get("username")
|
||||||
|
|
||||||
|
print(f"[*] Received {event_type} event from {repo_name} (by {sender})")
|
||||||
|
|
||||||
|
if event_type == "push":
|
||||||
|
self.handle_push(payload)
|
||||||
|
elif event_type == "pull_request":
|
||||||
|
self.handle_pr(payload)
|
||||||
|
elif event_type == "issue":
|
||||||
|
self.handle_issue(payload)
|
||||||
|
else:
|
||||||
|
print(f"[INFO] Ignoring event type: {event_type}")
|
||||||
|
|
||||||
|
def infer_event_type(self, payload: Dict[str, Any]) -> str:
|
||||||
|
if "commits" in payload: return "push"
|
||||||
|
if "pull_request" in payload: return "pull_request"
|
||||||
|
if "issue" in payload: return "issue"
|
||||||
|
return "unknown"
|
||||||
|
|
||||||
|
def handle_push(self, payload: Dict[str, Any]):
|
||||||
|
ref = payload.get("ref")
|
||||||
|
print(f" [PUSH] Branch: {ref}")
|
||||||
|
# Trigger CI or deployment
|
||||||
|
if ref == "refs/heads/main":
|
||||||
|
print(" [ACTION] Triggering production deployment...")
|
||||||
|
# Example: subprocess.run(["./deploy.sh"])
|
||||||
|
|
||||||
|
def handle_pr(self, payload: Dict[str, Any]):
|
||||||
|
action = payload.get("action")
|
||||||
|
pr_num = payload.get("pull_request", {}).get("number")
|
||||||
|
print(f" [PR] Action: {action} | PR #{pr_num}")
|
||||||
|
|
||||||
|
if action in ["opened", "synchronized"]:
|
||||||
|
print(f" [ACTION] Triggering architecture linter for PR #{pr_num}...")
|
||||||
|
# Example: subprocess.run(["python3", "scripts/architecture_linter_v2.py"])
|
||||||
|
|
||||||
|
def handle_issue(self, payload: Dict[str, Any]):
|
||||||
|
action = payload.get("action")
|
||||||
|
issue_num = payload.get("issue", {}).get("number")
|
||||||
|
print(f" [ISSUE] Action: {action} | Issue #{issue_num}")
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Gemini Webhook Handler")
|
||||||
|
parser.add_argument("payload_file", help="JSON file containing the webhook payload")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
if not os.path.exists(args.payload_file):
|
||||||
|
print(f"[ERROR] Payload file {args.payload_file} not found.")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
with open(args.payload_file, "r") as f:
|
||||||
|
try:
|
||||||
|
payload = json.load(f)
|
||||||
|
except:
|
||||||
|
print("[ERROR] Invalid JSON payload.")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
handler = WebhookHandler()
|
||||||
|
handler.handle_event(payload)
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
75
scripts/health_dashboard.py
Normal file
75
scripts/health_dashboard.py
Normal file
@@ -0,0 +1,75 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
health_dashboard.py — Sovereign Health & Observability Dashboard.
|
||||||
|
|
||||||
|
Aggregates data from Muda, Guardrails, Token Optimizer, and Quality Gates
|
||||||
|
into a single, unified health report for the Timmy Foundation fleet.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import json
|
||||||
|
import subprocess
|
||||||
|
from datetime import datetime
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
REPORTS_DIR = Path("reports")
|
||||||
|
DASHBOARD_FILE = Path("SOVEREIGN_HEALTH.md")
|
||||||
|
|
||||||
|
class HealthDashboard:
|
||||||
|
def __init__(self):
|
||||||
|
REPORTS_DIR.mkdir(exist_ok=True)
|
||||||
|
|
||||||
|
def run_tool(self, name: str, cmd: str) -> str:
|
||||||
|
print(f"[*] Running {name}...")
|
||||||
|
try:
|
||||||
|
# Capture output
|
||||||
|
res = subprocess.run(cmd, shell=True, capture_output=True, text=True)
|
||||||
|
return res.stdout
|
||||||
|
except Exception as e:
|
||||||
|
return f"Error running {name}: {e}"
|
||||||
|
|
||||||
|
def generate_report(self):
|
||||||
|
print("--- Generating Sovereign Health Dashboard ---")
|
||||||
|
|
||||||
|
# 1. Run Audits
|
||||||
|
muda_output = self.run_tool("Muda Audit", "python3 scripts/muda_audit.py")
|
||||||
|
guardrails_output = self.run_tool("Agent Guardrails", "python3 scripts/agent_guardrails.py")
|
||||||
|
optimizer_output = self.run_tool("Token Optimizer", "python3 scripts/token_optimizer.py")
|
||||||
|
gate_output = self.run_tool("Quality Gate", "python3 scripts/ci_automation_gate.py .")
|
||||||
|
|
||||||
|
# 2. Build Markdown
|
||||||
|
now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||||
|
md = [
|
||||||
|
f"# 🛡️ Sovereign Health Dashboard",
|
||||||
|
f"**Last Updated:** {now}",
|
||||||
|
f"",
|
||||||
|
f"## 📊 Summary",
|
||||||
|
f"- **Fleet Status:** ACTIVE",
|
||||||
|
f"- **Security Posture:** MONITORING",
|
||||||
|
f"- **Operational Waste:** AUDITED",
|
||||||
|
f"",
|
||||||
|
f"## ♻️ Muda Waste Audit",
|
||||||
|
f"```\n{muda_output}\n```",
|
||||||
|
f"",
|
||||||
|
f"## 🕵️ Agent Guardrails",
|
||||||
|
f"```\n{guardrails_output}\n```",
|
||||||
|
f"",
|
||||||
|
f"## 🪙 Token Efficiency",
|
||||||
|
f"```\n{optimizer_output}\n```",
|
||||||
|
f"",
|
||||||
|
f"## 🏗️ CI Quality Gate",
|
||||||
|
f"```\n{gate_output}\n```",
|
||||||
|
f"",
|
||||||
|
f"---",
|
||||||
|
f"*Generated by Sovereign Infrastructure Suite*"
|
||||||
|
]
|
||||||
|
|
||||||
|
with open(DASHBOARD_FILE, "w") as f:
|
||||||
|
f.write("\n".join(md))
|
||||||
|
|
||||||
|
print(f"[SUCCESS] Dashboard generated at {DASHBOARD_FILE}")
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
dashboard = HealthDashboard()
|
||||||
|
dashboard.generate_report()
|
||||||
388
scripts/knowledge_base.py
Normal file
388
scripts/knowledge_base.py
Normal file
@@ -0,0 +1,388 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""knowledge_base.py - GOFAI symbolic knowledge base for the Timmy Foundation fleet.
|
||||||
|
|
||||||
|
A classical AI knowledge representation system: stores facts as ground atoms,
|
||||||
|
supports first-order-logic-style queries, and maintains a provenance chain so
|
||||||
|
every belief can be traced back to its source. No neural nets, no embeddings -
|
||||||
|
just structured symbolic reasoning over a typed fact store.
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
kb = KnowledgeBase()
|
||||||
|
kb.assert_fact('agent', 'online', 'timmy')
|
||||||
|
kb.assert_fact('task', 'assigned_to', 'task-42', 'timmy')
|
||||||
|
results = kb.query('task', 'assigned_to', '?x', 'timmy')
|
||||||
|
# results -> [{'?x': 'task-42'}]
|
||||||
|
|
||||||
|
CLI:
|
||||||
|
python knowledge_base.py --assert "agent online hermes"
|
||||||
|
python knowledge_base.py --query "agent online ?who"
|
||||||
|
python knowledge_base.py --dump
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import ast
|
||||||
|
import json
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import time
|
||||||
|
from dataclasses import dataclass, field
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import Dict, Iterator, List, Optional, Tuple
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Data model
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
VAR_PREFIX = "?"
|
||||||
|
|
||||||
|
|
||||||
|
def is_var(term: str) -> bool:
|
||||||
|
"""Return True if *term* is a logic variable (starts with '?')."""
|
||||||
|
return term.startswith(VAR_PREFIX)
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class Fact:
|
||||||
|
"""An immutable ground atom: (relation, *args)."""
|
||||||
|
|
||||||
|
relation: str
|
||||||
|
args: Tuple[str, ...]
|
||||||
|
source: str = "user"
|
||||||
|
timestamp: float = field(default_factory=time.time)
|
||||||
|
|
||||||
|
def __str__(self) -> str:
|
||||||
|
args_str = " ".join(self.args)
|
||||||
|
return f"({self.relation} {args_str})"
|
||||||
|
|
||||||
|
|
||||||
|
Bindings = Dict[str, str]
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Unification
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
|
||||||
|
def unify_term(pattern: str, value: str, bindings: Bindings) -> Optional[Bindings]:
|
||||||
|
"""Unify a single pattern term against a ground value.
|
||||||
|
|
||||||
|
Returns updated bindings on success, or None on failure.
|
||||||
|
"""
|
||||||
|
if is_var(pattern):
|
||||||
|
if pattern in bindings:
|
||||||
|
return bindings if bindings[pattern] == value else None
|
||||||
|
return {**bindings, pattern: value}
|
||||||
|
return bindings if pattern == value else None
|
||||||
|
|
||||||
|
|
||||||
|
def unify_fact(
|
||||||
|
pattern: Tuple[str, ...], fact_args: Tuple[str, ...], bindings: Bindings
|
||||||
|
) -> Optional[Bindings]:
|
||||||
|
"""Unify a full argument tuple, returning final bindings or None."""
|
||||||
|
if len(pattern) != len(fact_args):
|
||||||
|
return None
|
||||||
|
b = bindings
|
||||||
|
for p, v in zip(pattern, fact_args):
|
||||||
|
b = unify_term(p, v, b)
|
||||||
|
if b is None:
|
||||||
|
return None
|
||||||
|
return b
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Knowledge Base
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
|
||||||
|
class KnowledgeBase:
|
||||||
|
"""In-memory symbolic knowledge base with optional JSON persistence."""
|
||||||
|
|
||||||
|
def __init__(self, persist_path: Optional[Path] = None) -> None:
|
||||||
|
self._facts: List[Fact] = []
|
||||||
|
self._persist_path = persist_path
|
||||||
|
if persist_path and persist_path.exists():
|
||||||
|
self._load(persist_path)
|
||||||
|
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
# Fact management
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
|
||||||
|
def assert_fact(
|
||||||
|
self, relation: str, *args: str, source: str = "user"
|
||||||
|
) -> Fact:
|
||||||
|
"""Add a ground fact to the knowledge base.
|
||||||
|
|
||||||
|
Idempotent: duplicate (relation, args) pairs are not added twice.
|
||||||
|
"""
|
||||||
|
f = Fact(relation=relation, args=tuple(args), source=source, timestamp=time.time())
|
||||||
|
for existing in self._facts:
|
||||||
|
if existing.relation == f.relation and existing.args == f.args:
|
||||||
|
return existing # already known
|
||||||
|
self._facts.append(f)
|
||||||
|
if self._persist_path:
|
||||||
|
self._save(self._persist_path)
|
||||||
|
return f
|
||||||
|
|
||||||
|
def retract_fact(self, relation: str, *args: str) -> int:
|
||||||
|
"""Remove all facts matching (relation, *args). Returns count removed."""
|
||||||
|
before = len(self._facts)
|
||||||
|
self._facts = [
|
||||||
|
f
|
||||||
|
for f in self._facts
|
||||||
|
if not (f.relation == relation and f.args == tuple(args))
|
||||||
|
]
|
||||||
|
removed = before - len(self._facts)
|
||||||
|
if removed and self._persist_path:
|
||||||
|
self._save(self._persist_path)
|
||||||
|
return removed
|
||||||
|
|
||||||
|
def ingest_python_file(
|
||||||
|
self, path: Path, *, module_name: Optional[str] = None, source: str = "ast"
|
||||||
|
) -> List[Fact]:
|
||||||
|
"""Parse a Python file with ``ast`` and assert symbolic structure facts."""
|
||||||
|
tree = ast.parse(path.read_text(), filename=str(path))
|
||||||
|
module = module_name or path.stem
|
||||||
|
fact_source = f"{source}:{path.name}"
|
||||||
|
added: List[Fact] = []
|
||||||
|
|
||||||
|
def add(relation: str, *args: str) -> None:
|
||||||
|
added.append(self.assert_fact(relation, *args, source=fact_source))
|
||||||
|
|
||||||
|
for node in tree.body:
|
||||||
|
if isinstance(node, ast.Import):
|
||||||
|
for alias in node.names:
|
||||||
|
add("imports", module, alias.name)
|
||||||
|
elif isinstance(node, ast.ImportFrom):
|
||||||
|
prefix = f"{node.module}." if node.module else ""
|
||||||
|
for alias in node.names:
|
||||||
|
add("imports", module, f"{prefix}{alias.name}")
|
||||||
|
elif isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)):
|
||||||
|
add("defines_function", module, node.name)
|
||||||
|
elif isinstance(node, ast.ClassDef):
|
||||||
|
add("defines_class", module, node.name)
|
||||||
|
for child in node.body:
|
||||||
|
if isinstance(child, (ast.FunctionDef, ast.AsyncFunctionDef)):
|
||||||
|
add("defines_method", node.name, child.name)
|
||||||
|
elif isinstance(node, ast.Assign):
|
||||||
|
for target in node.targets:
|
||||||
|
if isinstance(target, ast.Name) and target.id.isupper():
|
||||||
|
add("defines_constant", module, target.id)
|
||||||
|
elif isinstance(node, ast.AnnAssign) and isinstance(node.target, ast.Name) and node.target.id.isupper():
|
||||||
|
add("defines_constant", module, node.target.id)
|
||||||
|
|
||||||
|
return added
|
||||||
|
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
# Query
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
|
||||||
|
def query(
|
||||||
|
self, relation: str, *pattern_args: str, source_filter: Optional[str] = None
|
||||||
|
) -> List[Bindings]:
|
||||||
|
"""Return all binding dictionaries satisfying the query pattern.
|
||||||
|
|
||||||
|
Variables in *pattern_args* start with '?'. Ground terms must match
|
||||||
|
exactly. An empty binding dict means the fact matched with no
|
||||||
|
variables to bind.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
relation: The relation name to match.
|
||||||
|
*pattern_args: Mixed ground/variable argument tuple.
|
||||||
|
source_filter: Optional provenance filter (e.g. 'scheduler').
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
List of binding dicts, one per matching fact.
|
||||||
|
"""
|
||||||
|
results: List[Bindings] = []
|
||||||
|
for fact in self._facts:
|
||||||
|
if fact.relation != relation:
|
||||||
|
continue
|
||||||
|
if source_filter and fact.source != source_filter:
|
||||||
|
continue
|
||||||
|
b = unify_fact(tuple(pattern_args), fact.args, {})
|
||||||
|
if b is not None:
|
||||||
|
results.append(b)
|
||||||
|
return results
|
||||||
|
|
||||||
|
def query_one(
|
||||||
|
self, relation: str, *pattern_args: str
|
||||||
|
) -> Optional[Bindings]:
|
||||||
|
"""Return the first matching binding dict or None."""
|
||||||
|
for b in self.query(relation, *pattern_args):
|
||||||
|
return b
|
||||||
|
return None
|
||||||
|
|
||||||
|
def facts_for(self, relation: str) -> Iterator[Fact]:
|
||||||
|
"""Iterate over all facts with the given relation."""
|
||||||
|
for f in self._facts:
|
||||||
|
if f.relation == relation:
|
||||||
|
yield f
|
||||||
|
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
# Bulk operations
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
|
||||||
|
def all_facts(self) -> List[Fact]:
|
||||||
|
"""Return a snapshot of all stored facts."""
|
||||||
|
return list(self._facts)
|
||||||
|
|
||||||
|
def fact_count(self) -> int:
|
||||||
|
return len(self._facts)
|
||||||
|
|
||||||
|
def clear(self) -> None:
|
||||||
|
"""Remove all facts from memory (does not touch disk)."""
|
||||||
|
self._facts.clear()
|
||||||
|
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
# Persistence
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
|
||||||
|
def _save(self, path: Path) -> None:
|
||||||
|
records = [
|
||||||
|
{
|
||||||
|
"relation": f.relation,
|
||||||
|
"args": list(f.args),
|
||||||
|
"source": f.source,
|
||||||
|
"timestamp": f.timestamp,
|
||||||
|
}
|
||||||
|
for f in self._facts
|
||||||
|
]
|
||||||
|
path.write_text(json.dumps(records, indent=2))
|
||||||
|
|
||||||
|
def _load(self, path: Path) -> None:
|
||||||
|
try:
|
||||||
|
records = json.loads(path.read_text())
|
||||||
|
for r in records:
|
||||||
|
self._facts.append(
|
||||||
|
Fact(
|
||||||
|
relation=r["relation"],
|
||||||
|
args=tuple(r["args"]),
|
||||||
|
source=r.get("source", "persisted"),
|
||||||
|
timestamp=r.get("timestamp", 0.0),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
except (json.JSONDecodeError, KeyError) as exc:
|
||||||
|
print(f"[kb] Warning: could not load {path}: {exc}", file=sys.stderr)
|
||||||
|
|
||||||
|
def save_to(self, path: Path) -> None:
|
||||||
|
"""Explicitly save to a given path."""
|
||||||
|
self._save(path)
|
||||||
|
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
# Debug / display
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
|
||||||
|
def dump(self, relation_filter: Optional[str] = None) -> None:
|
||||||
|
"""Print all (or filtered) facts to stdout."""
|
||||||
|
for f in self._facts:
|
||||||
|
if relation_filter and f.relation != relation_filter:
|
||||||
|
continue
|
||||||
|
print(f" {f} [source={f.source}]")
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# CLI
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
|
||||||
|
def _parse_terms(raw: str) -> List[str]:
|
||||||
|
"""Split a whitespace-separated string into terms."""
|
||||||
|
return raw.strip().split()
|
||||||
|
|
||||||
|
|
||||||
|
def main() -> None:
|
||||||
|
parser = argparse.ArgumentParser(
|
||||||
|
description="GOFAI symbolic knowledge base CLI"
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--db",
|
||||||
|
default="kb.json",
|
||||||
|
help="Path to persistent JSON store (default: kb.json)",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--assert",
|
||||||
|
dest="assert_stmt",
|
||||||
|
metavar="RELATION ARG...",
|
||||||
|
help='Assert a fact, e.g. --assert "agent online timmy"',
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--retract",
|
||||||
|
dest="retract_stmt",
|
||||||
|
metavar="RELATION ARG...",
|
||||||
|
help='Retract a fact, e.g. --retract "agent online timmy"',
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--query",
|
||||||
|
dest="query_stmt",
|
||||||
|
metavar="RELATION ARG...",
|
||||||
|
help='Query the KB, e.g. --query "agent online ?who"',
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--dump",
|
||||||
|
action="store_true",
|
||||||
|
help="Dump all facts",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--ingest-python",
|
||||||
|
dest="ingest_python",
|
||||||
|
type=Path,
|
||||||
|
help="Parse a Python file with AST and assert symbolic structure facts",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--relation",
|
||||||
|
help="Filter --dump to a specific relation",
|
||||||
|
)
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
db_path = Path(args.db)
|
||||||
|
kb = KnowledgeBase(persist_path=db_path)
|
||||||
|
|
||||||
|
if args.assert_stmt:
|
||||||
|
terms = _parse_terms(args.assert_stmt)
|
||||||
|
if len(terms) < 2:
|
||||||
|
print("ERROR: --assert requires at least RELATION and one ARG", file=sys.stderr)
|
||||||
|
sys.exit(1)
|
||||||
|
fact = kb.assert_fact(terms[0], *terms[1:], source="cli")
|
||||||
|
print(f"Asserted: {fact}")
|
||||||
|
|
||||||
|
if args.ingest_python:
|
||||||
|
added = kb.ingest_python_file(args.ingest_python, source="cli-ast")
|
||||||
|
print(f"Ingested {len(added)} AST fact(s) from {args.ingest_python}")
|
||||||
|
|
||||||
|
if args.retract_stmt:
|
||||||
|
terms = _parse_terms(args.retract_stmt)
|
||||||
|
if len(terms) < 2:
|
||||||
|
print("ERROR: --retract requires at least RELATION and one ARG", file=sys.stderr)
|
||||||
|
sys.exit(1)
|
||||||
|
n = kb.retract_fact(terms[0], *terms[1:])
|
||||||
|
print(f"Retracted {n} fact(s).")
|
||||||
|
|
||||||
|
if args.query_stmt:
|
||||||
|
terms = _parse_terms(args.query_stmt)
|
||||||
|
if len(terms) < 2:
|
||||||
|
print("ERROR: --query requires at least RELATION and one ARG", file=sys.stderr)
|
||||||
|
sys.exit(1)
|
||||||
|
results = kb.query(terms[0], *terms[1:])
|
||||||
|
if not results:
|
||||||
|
print("No results.")
|
||||||
|
else:
|
||||||
|
for i, b in enumerate(results, 1):
|
||||||
|
if b:
|
||||||
|
bindings_str = ", ".join(f"{k}={v}" for k, v in b.items())
|
||||||
|
print(f" [{i}] {bindings_str}")
|
||||||
|
else:
|
||||||
|
print(f" [{i}] (ground match)")
|
||||||
|
|
||||||
|
if args.dump:
|
||||||
|
count = kb.fact_count()
|
||||||
|
print(f"Knowledge Base — {count} fact(s):")
|
||||||
|
kb.dump(relation_filter=args.relation)
|
||||||
|
|
||||||
|
if not any([args.assert_stmt, args.retract_stmt, args.query_stmt, args.dump]):
|
||||||
|
parser.print_help()
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
12
scripts/matrix_glitch_detect.py
Normal file
12
scripts/matrix_glitch_detect.py
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
import json
|
||||||
|
from hermes_tools import browser_navigate, browser_vision
|
||||||
|
|
||||||
|
def detect_glitches():
|
||||||
|
browser_navigate(url="https://matrix.alexanderwhitestone.com")
|
||||||
|
analysis = browser_vision(
|
||||||
|
question="Scan the 3D world for visual artifacts, floating assets, or z-fighting. List all coordinates/descriptions of glitches found. Provide a PASS/FAIL."
|
||||||
|
)
|
||||||
|
return {"status": "PASS" if "PASS" in analysis.upper() else "FAIL", "analysis": analysis}
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
print(json.dumps(detect_glitches(), indent=2))
|
||||||
95
scripts/model_eval.py
Normal file
95
scripts/model_eval.py
Normal file
@@ -0,0 +1,95 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[EVAL] Model Evaluation Harness
|
||||||
|
Part of the Gemini Sovereign Infrastructure Suite.
|
||||||
|
|
||||||
|
Benchmarks GGUF models for speed and quality before deployment.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import time
|
||||||
|
import json
|
||||||
|
import argparse
|
||||||
|
import requests
|
||||||
|
|
||||||
|
BENCHMARK_PROMPTS = [
|
||||||
|
"Write a Python script to sort a list of dictionaries by a key.",
|
||||||
|
"Explain the concept of 'Sovereign AI' in three sentences.",
|
||||||
|
"What is the capital of France?",
|
||||||
|
"Write a short story about a robot learning to paint."
|
||||||
|
]
|
||||||
|
|
||||||
|
class ModelEval:
|
||||||
|
def __init__(self, endpoint: str):
|
||||||
|
self.endpoint = endpoint.rstrip("/")
|
||||||
|
|
||||||
|
def log(self, message: str):
|
||||||
|
print(f"[*] {message}")
|
||||||
|
|
||||||
|
def run_benchmark(self):
|
||||||
|
self.log(f"Starting benchmark for {self.endpoint}...")
|
||||||
|
results = []
|
||||||
|
|
||||||
|
for prompt in BENCHMARK_PROMPTS:
|
||||||
|
self.log(f"Testing prompt: {prompt[:30]}...")
|
||||||
|
|
||||||
|
start_time = time.time()
|
||||||
|
try:
|
||||||
|
# llama.cpp server /completion endpoint
|
||||||
|
response = requests.post(
|
||||||
|
f"{self.endpoint}/completion",
|
||||||
|
json={"prompt": prompt, "n_predict": 128},
|
||||||
|
timeout=60
|
||||||
|
)
|
||||||
|
duration = time.time() - start_time
|
||||||
|
|
||||||
|
if response.status_code == 200:
|
||||||
|
data = response.json()
|
||||||
|
content = data.get("content", "")
|
||||||
|
# Rough estimate of tokens (4 chars per token is a common rule of thumb)
|
||||||
|
tokens = len(content) / 4
|
||||||
|
tps = tokens / duration
|
||||||
|
|
||||||
|
results.append({
|
||||||
|
"prompt": prompt,
|
||||||
|
"duration": duration,
|
||||||
|
"tps": tps,
|
||||||
|
"success": True
|
||||||
|
})
|
||||||
|
else:
|
||||||
|
results.append({"prompt": prompt, "success": False, "error": response.text})
|
||||||
|
except Exception as e:
|
||||||
|
results.append({"prompt": prompt, "success": False, "error": str(e)})
|
||||||
|
|
||||||
|
self.report(results)
|
||||||
|
|
||||||
|
def report(self, results: list):
|
||||||
|
print("\n--- Evaluation Report ---")
|
||||||
|
total_tps = 0
|
||||||
|
success_count = 0
|
||||||
|
|
||||||
|
for r in results:
|
||||||
|
if r["success"]:
|
||||||
|
print(f"✅ {r['prompt'][:40]}... | {r['tps']:.2f} tok/s | {r['duration']:.2f}s")
|
||||||
|
total_tps += r["tps"]
|
||||||
|
success_count += 1
|
||||||
|
else:
|
||||||
|
print(f"❌ {r['prompt'][:40]}... | FAILED: {r['error']}")
|
||||||
|
|
||||||
|
if success_count > 0:
|
||||||
|
avg_tps = total_tps / success_count
|
||||||
|
print(f"\nAverage Performance: {avg_tps:.2f} tok/s")
|
||||||
|
else:
|
||||||
|
print("\n[FAILURE] All benchmarks failed.")
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Gemini Model Eval")
|
||||||
|
parser.add_argument("endpoint", help="llama-server endpoint (e.g. http://localhost:8080)")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
evaluator = ModelEval(args.endpoint)
|
||||||
|
evaluator.run_benchmark()
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
20
scripts/nexus_smoke_test.py
Normal file
20
scripts/nexus_smoke_test.py
Normal file
@@ -0,0 +1,20 @@
|
|||||||
|
import json
|
||||||
|
from hermes_tools import browser_navigate, browser_vision
|
||||||
|
|
||||||
|
def run_smoke_test():
|
||||||
|
print("Navigating to The Nexus...")
|
||||||
|
browser_navigate(url="https://nexus.alexanderwhitestone.com")
|
||||||
|
|
||||||
|
print("Performing visual verification...")
|
||||||
|
analysis = browser_vision(
|
||||||
|
question="Is the Nexus landing page rendered correctly? Check for: 1) The Tower logo, 2) The main entry portal, 3) Absence of 404/Error messages. Provide a clear PASS or FAIL."
|
||||||
|
)
|
||||||
|
|
||||||
|
result = {
|
||||||
|
"status": "PASS" if "PASS" in analysis.upper() else "FAIL",
|
||||||
|
"analysis": analysis
|
||||||
|
}
|
||||||
|
return result
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
print(json.dumps(run_smoke_test(), indent=2))
|
||||||
114
scripts/phase_tracker.py
Normal file
114
scripts/phase_tracker.py
Normal file
@@ -0,0 +1,114 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[OPS] Phase Progression Tracker
|
||||||
|
Part of the Gemini Sovereign Infrastructure Suite.
|
||||||
|
|
||||||
|
Tracks the fleet's progress through the Paperclips-inspired evolution arc.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import json
|
||||||
|
import argparse
|
||||||
|
|
||||||
|
MILESTONES_FILE = "fleet/milestones.md"
|
||||||
|
COMPLETED_FILE = "fleet/completed_milestones.json"
|
||||||
|
|
||||||
|
class PhaseTracker:
|
||||||
|
def __init__(self):
|
||||||
|
# Find files relative to repo root
|
||||||
|
script_dir = os.path.dirname(os.path.abspath(__file__))
|
||||||
|
repo_root = os.path.dirname(script_dir)
|
||||||
|
|
||||||
|
self.milestones_path = os.path.join(repo_root, MILESTONES_FILE)
|
||||||
|
self.completed_path = os.path.join(repo_root, COMPLETED_FILE)
|
||||||
|
|
||||||
|
self.milestones = self.parse_milestones()
|
||||||
|
self.completed = self.load_completed()
|
||||||
|
|
||||||
|
def parse_milestones(self):
|
||||||
|
if not os.path.exists(self.milestones_path):
|
||||||
|
return {}
|
||||||
|
|
||||||
|
with open(self.milestones_path, "r") as f:
|
||||||
|
content = f.read()
|
||||||
|
|
||||||
|
phases = {}
|
||||||
|
current_phase = None
|
||||||
|
|
||||||
|
for line in content.split("\n"):
|
||||||
|
if line.startswith("## Phase"):
|
||||||
|
current_phase = line.replace("## ", "").strip()
|
||||||
|
phases[current_phase] = []
|
||||||
|
elif line.startswith("### M"):
|
||||||
|
m_id = line.split(":")[0].replace("### ", "").strip()
|
||||||
|
title = line.split(":")[1].strip()
|
||||||
|
phases[current_phase].append({"id": m_id, "title": title})
|
||||||
|
|
||||||
|
return phases
|
||||||
|
|
||||||
|
def load_completed(self):
|
||||||
|
if os.path.exists(self.completed_path):
|
||||||
|
with open(self.completed_path, "r") as f:
|
||||||
|
try:
|
||||||
|
return json.load(f)
|
||||||
|
except:
|
||||||
|
return []
|
||||||
|
return []
|
||||||
|
|
||||||
|
def save_completed(self):
|
||||||
|
with open(self.completed_path, "w") as f:
|
||||||
|
json.dump(self.completed, f, indent=2)
|
||||||
|
|
||||||
|
def show_progress(self):
|
||||||
|
print("--- Fleet Phase Progression Tracker ---")
|
||||||
|
total_milestones = 0
|
||||||
|
total_completed = 0
|
||||||
|
|
||||||
|
if not self.milestones:
|
||||||
|
print("[ERROR] No milestones found in fleet/milestones.md")
|
||||||
|
return
|
||||||
|
|
||||||
|
for phase, ms in self.milestones.items():
|
||||||
|
print(f"\n{phase}")
|
||||||
|
for m in ms:
|
||||||
|
total_milestones += 1
|
||||||
|
done = m["id"] in self.completed
|
||||||
|
if done:
|
||||||
|
total_completed += 1
|
||||||
|
status = "✅" if done else "⭕"
|
||||||
|
print(f" {status} {m['id']}: {m['title']}")
|
||||||
|
|
||||||
|
percent = (total_completed / total_milestones) * 100 if total_milestones > 0 else 0
|
||||||
|
print(f"\nOverall Progress: {total_completed}/{total_milestones} ({percent:.1f}%)")
|
||||||
|
|
||||||
|
def mark_complete(self, m_id: str):
|
||||||
|
if m_id not in self.completed:
|
||||||
|
self.completed.append(m_id)
|
||||||
|
self.save_completed()
|
||||||
|
print(f"[SUCCESS] Marked {m_id} as complete.")
|
||||||
|
else:
|
||||||
|
print(f"[INFO] {m_id} is already complete.")
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Gemini Phase Tracker")
|
||||||
|
subparsers = parser.add_subparsers(dest="command")
|
||||||
|
|
||||||
|
subparsers.add_parser("status", help="Show current progress")
|
||||||
|
|
||||||
|
complete_parser = subparsers.add_parser("complete", help="Mark a milestone as complete")
|
||||||
|
complete_parser.add_argument("id", help="Milestone ID (e.g. M1)")
|
||||||
|
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
tracker = PhaseTracker()
|
||||||
|
|
||||||
|
if args.command == "status":
|
||||||
|
tracker.show_progress()
|
||||||
|
elif args.command == "complete":
|
||||||
|
tracker.mark_complete(args.id)
|
||||||
|
else:
|
||||||
|
parser.print_help()
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
229
scripts/provision_wizard.py
Normal file
229
scripts/provision_wizard.py
Normal file
@@ -0,0 +1,229 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[OPS] Automated VPS Provisioning System (Von Neumann as Code)
|
||||||
|
Part of the Gemini Sovereign Infrastructure Suite.
|
||||||
|
|
||||||
|
This script automates the creation and configuration of a "Wizard" node
|
||||||
|
from zero to serving inference via llama.cpp.
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
python3 provision_wizard.py --name fenrir --size s-2vcpu-4gb --model qwen2.5-coder-7b
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import time
|
||||||
|
import argparse
|
||||||
|
import requests
|
||||||
|
import json
|
||||||
|
from typing import Optional, Dict, Any
|
||||||
|
|
||||||
|
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||||
|
if SCRIPT_DIR not in sys.path:
|
||||||
|
sys.path.insert(0, SCRIPT_DIR)
|
||||||
|
|
||||||
|
from ssh_trust import VerifiedSSHExecutor
|
||||||
|
|
||||||
|
# --- CONFIGURATION ---
|
||||||
|
DO_API_URL = "https://api.digitalocean.com/v2"
|
||||||
|
# We expect DIGITALOCEAN_TOKEN to be set in the environment.
|
||||||
|
DO_TOKEN = os.environ.get("DIGITALOCEAN_TOKEN")
|
||||||
|
|
||||||
|
# Default settings
|
||||||
|
DEFAULT_REGION = "nyc3"
|
||||||
|
DEFAULT_IMAGE = "ubuntu-22-04-x64"
|
||||||
|
LLAMA_CPP_REPO = "https://github.com/ggerganov/llama.cpp"
|
||||||
|
|
||||||
|
class Provisioner:
|
||||||
|
def __init__(self, name: str, size: str, model: str, region: str = DEFAULT_REGION, executor=None):
|
||||||
|
self.name = name
|
||||||
|
self.size = size
|
||||||
|
self.model = model
|
||||||
|
self.region = region
|
||||||
|
self.droplet_id = None
|
||||||
|
self.ip_address = None
|
||||||
|
self.executor = executor or VerifiedSSHExecutor(auto_enroll=True)
|
||||||
|
|
||||||
|
def log(self, message: str):
|
||||||
|
print(f"[*] {message}")
|
||||||
|
|
||||||
|
def error(self, message: str):
|
||||||
|
print(f"[!] ERROR: {message}")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
def check_auth(self):
|
||||||
|
if not DO_TOKEN:
|
||||||
|
self.error("DIGITALOCEAN_TOKEN environment variable not set.")
|
||||||
|
|
||||||
|
def create_droplet(self):
|
||||||
|
self.log(f"Creating droplet '{self.name}' ({self.size}) in {self.region}...")
|
||||||
|
|
||||||
|
# Get SSH keys to add to the droplet
|
||||||
|
ssh_keys = self.get_ssh_keys()
|
||||||
|
|
||||||
|
payload = {
|
||||||
|
"name": self.name,
|
||||||
|
"region": self.region,
|
||||||
|
"size": self.size,
|
||||||
|
"image": DEFAULT_IMAGE,
|
||||||
|
"ssh_keys": ssh_keys,
|
||||||
|
"backups": False,
|
||||||
|
"ipv6": True,
|
||||||
|
"monitoring": True,
|
||||||
|
"tags": ["wizard", "gemini-provisioned"]
|
||||||
|
}
|
||||||
|
|
||||||
|
headers = {
|
||||||
|
"Authorization": f"Bearer {DO_TOKEN}",
|
||||||
|
"Content-Type": "application/json"
|
||||||
|
}
|
||||||
|
|
||||||
|
response = requests.post(f"{DO_API_URL}/droplets", json=payload, headers=headers)
|
||||||
|
if response.status_code != 202:
|
||||||
|
self.error(f"Failed to create droplet: {response.text}")
|
||||||
|
|
||||||
|
data = response.json()
|
||||||
|
self.droplet_id = data["droplet"]["id"]
|
||||||
|
self.log(f"Droplet created (ID: {self.droplet_id}). Waiting for IP...")
|
||||||
|
|
||||||
|
def get_ssh_keys(self) -> list:
|
||||||
|
# Fetch existing SSH keys from DO account to ensure we can log in
|
||||||
|
headers = {"Authorization": f"Bearer {DO_TOKEN}"}
|
||||||
|
response = requests.get(f"{DO_API_URL}/account/keys", headers=headers)
|
||||||
|
if response.status_code != 200:
|
||||||
|
self.log("Warning: Could not fetch SSH keys. Droplet might be inaccessible via SSH.")
|
||||||
|
return []
|
||||||
|
return [key["id"] for key in response.json()["ssh_keys"]]
|
||||||
|
|
||||||
|
def wait_for_ip(self):
|
||||||
|
headers = {"Authorization": f"Bearer {DO_TOKEN}"}
|
||||||
|
while not self.ip_address:
|
||||||
|
response = requests.get(f"{DO_API_URL}/droplets/{self.droplet_id}", headers=headers)
|
||||||
|
data = response.json()
|
||||||
|
networks = data["droplet"]["networks"]["v4"]
|
||||||
|
for net in networks:
|
||||||
|
if net["type"] == "public":
|
||||||
|
self.ip_address = net["ip_address"]
|
||||||
|
break
|
||||||
|
if not self.ip_address:
|
||||||
|
time.sleep(5)
|
||||||
|
self.log(f"Droplet IP: {self.ip_address}")
|
||||||
|
|
||||||
|
def run_remote(self, command: str):
|
||||||
|
# Uses verified host trust. Brand-new nodes explicitly enroll on first contact.
|
||||||
|
return self.executor.run_script(self.ip_address, command, timeout=60)
|
||||||
|
|
||||||
|
def setup_wizard(self):
|
||||||
|
self.log("Starting remote setup...")
|
||||||
|
|
||||||
|
# Wait for SSH to be ready
|
||||||
|
retries = 12
|
||||||
|
while retries > 0:
|
||||||
|
res = self.run_remote("echo 'SSH Ready'")
|
||||||
|
if res.returncode == 0:
|
||||||
|
break
|
||||||
|
self.log(f"Waiting for SSH... ({retries} retries left)")
|
||||||
|
time.sleep(10)
|
||||||
|
retries -= 1
|
||||||
|
|
||||||
|
if retries == 0:
|
||||||
|
self.error("SSH timed out.")
|
||||||
|
|
||||||
|
# 1. Update and install dependencies
|
||||||
|
self.log("Installing dependencies...")
|
||||||
|
setup_script = """
|
||||||
|
export DEBIAN_FRONTEND=noninteractive
|
||||||
|
apt-get update && apt-get upgrade -y
|
||||||
|
apt-get install -y build-essential git cmake curl wget python3 python3-pip
|
||||||
|
"""
|
||||||
|
self.run_remote(setup_script)
|
||||||
|
|
||||||
|
# 2. Build llama.cpp
|
||||||
|
self.log("Building llama.cpp...")
|
||||||
|
build_script = f"""
|
||||||
|
if [ ! -d "/opt/llama.cpp" ]; then
|
||||||
|
git clone {LLAMA_CPP_REPO} /opt/llama.cpp
|
||||||
|
fi
|
||||||
|
cd /opt/llama.cpp
|
||||||
|
mkdir -p build && cd build
|
||||||
|
cmake ..
|
||||||
|
cmake --build . --config Release
|
||||||
|
"""
|
||||||
|
self.run_remote(build_script)
|
||||||
|
|
||||||
|
# 3. Download Model
|
||||||
|
self.log(f"Downloading model: {self.model}...")
|
||||||
|
model_url = self.get_model_url(self.model)
|
||||||
|
download_script = f"""
|
||||||
|
mkdir -p /opt/models
|
||||||
|
if [ ! -f "/opt/models/{self.model}.gguf" ]; then
|
||||||
|
wget -O /opt/models/{self.model}.gguf {model_url}
|
||||||
|
fi
|
||||||
|
"""
|
||||||
|
self.run_remote(download_script)
|
||||||
|
|
||||||
|
# 4. Create systemd service
|
||||||
|
self.log("Creating systemd service...")
|
||||||
|
service_content = f"""
|
||||||
|
[Unit]
|
||||||
|
Description=Llama.cpp Server for {self.name}
|
||||||
|
After=network.target
|
||||||
|
|
||||||
|
[Service]
|
||||||
|
Type=simple
|
||||||
|
User=root
|
||||||
|
WorkingDirectory=/opt/llama.cpp
|
||||||
|
ExecStart=/opt/llama.cpp/build/bin/llama-server -m /opt/models/{self.model}.gguf --host 0.0.0.0 --port 8080 -c 4096
|
||||||
|
Restart=always
|
||||||
|
RestartSec=10
|
||||||
|
|
||||||
|
[Install]
|
||||||
|
WantedBy=multi-user.target
|
||||||
|
"""
|
||||||
|
# Use cat to write the file to handle multi-line string safely
|
||||||
|
self.run_remote(f"cat <<EOF > /etc/systemd/system/llama-server.service\n{service_content}\nEOF")
|
||||||
|
self.run_remote("systemctl daemon-reload && systemctl enable llama-server && systemctl start llama-server")
|
||||||
|
|
||||||
|
def get_model_url(self, model_name: str) -> str:
|
||||||
|
# Mapping for common models to GGUF URLs (HuggingFace)
|
||||||
|
mapping = {
|
||||||
|
"qwen2.5-coder-7b": "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF/resolve/main/qwen2.5-coder-7b-instruct-q4_k_m.gguf",
|
||||||
|
"hermes-3-llama-3.1-8b": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B-GGUF/resolve/main/Hermes-3-Llama-3.1-8B.Q4_K_M.gguf"
|
||||||
|
}
|
||||||
|
return mapping.get(model_name, mapping["hermes-3-llama-3.1-8b"])
|
||||||
|
|
||||||
|
def health_check(self):
|
||||||
|
self.log("Performing health check...")
|
||||||
|
time.sleep(15) # Wait for server to start
|
||||||
|
try:
|
||||||
|
url = f"http://{self.ip_address}:8080/health"
|
||||||
|
response = requests.get(url, timeout=10)
|
||||||
|
if response.status_code == 200:
|
||||||
|
self.log(f"[SUCCESS] Wizard {self.name} is healthy and serving inference.")
|
||||||
|
self.log(f"Endpoint: {url}")
|
||||||
|
else:
|
||||||
|
self.log(f"[WARNING] Health check returned status {response.status_code}")
|
||||||
|
except Exception as e:
|
||||||
|
self.log(f"[ERROR] Health check failed: {e}")
|
||||||
|
|
||||||
|
def provision(self):
|
||||||
|
self.check_auth()
|
||||||
|
self.create_droplet()
|
||||||
|
self.wait_for_ip()
|
||||||
|
self.setup_wizard()
|
||||||
|
self.health_check()
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Gemini Provisioner")
|
||||||
|
parser.add_argument("--name", required=True, help="Name of the wizard")
|
||||||
|
parser.add_argument("--size", default="s-2vcpu-4gb", help="DO droplet size")
|
||||||
|
parser.add_argument("--model", default="qwen2.5-coder-7b", help="Model to serve")
|
||||||
|
parser.add_argument("--region", default="nyc3", help="DO region")
|
||||||
|
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
provisioner = Provisioner(args.name, args.size, args.model, args.region)
|
||||||
|
provisioner.provision()
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
240
scripts/self_healing.py
Normal file
240
scripts/self_healing.py
Normal file
@@ -0,0 +1,240 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[OPS] Self-Healing Infrastructure
|
||||||
|
Part of the Gemini Sovereign Infrastructure Suite.
|
||||||
|
|
||||||
|
Auto-detects and fixes common failures across the fleet.
|
||||||
|
|
||||||
|
Safe-by-default: runs in dry-run mode unless --execute is given.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import argparse
|
||||||
|
import requests
|
||||||
|
import datetime
|
||||||
|
from typing import Sequence
|
||||||
|
|
||||||
|
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||||
|
if SCRIPT_DIR not in sys.path:
|
||||||
|
sys.path.insert(0, SCRIPT_DIR)
|
||||||
|
|
||||||
|
from ssh_trust import VerifiedSSHExecutor
|
||||||
|
|
||||||
|
# --- CONFIGURATION ---
|
||||||
|
FLEET = {
|
||||||
|
"mac": {"ip": "10.1.10.77", "port": 8080},
|
||||||
|
"ezra": {"ip": "143.198.27.163", "port": 8080},
|
||||||
|
"allegro": {"ip": "167.99.126.228", "port": 8080},
|
||||||
|
"bezalel": {"ip": "159.203.146.185", "port": 8080}
|
||||||
|
}
|
||||||
|
|
||||||
|
class SelfHealer:
|
||||||
|
def __init__(self, dry_run=True, confirm_kill=False, yes=False, executor=None):
|
||||||
|
self.dry_run = dry_run
|
||||||
|
self.confirm_kill = confirm_kill
|
||||||
|
self.yes = yes
|
||||||
|
self.executor = executor or VerifiedSSHExecutor()
|
||||||
|
|
||||||
|
def log(self, message: str):
|
||||||
|
timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||||
|
print(f"[{timestamp}] {message}")
|
||||||
|
|
||||||
|
def run_remote(self, host: str, command: str):
|
||||||
|
ip = FLEET[host]['ip']
|
||||||
|
try:
|
||||||
|
return self.executor.run_script(ip, command, local=(host == 'mac'), timeout=15)
|
||||||
|
except Exception as e:
|
||||||
|
self.log(f" [ERROR] Failed to run remote command on {host}: {e}")
|
||||||
|
return None
|
||||||
|
|
||||||
|
def confirm(self, prompt: str) -> bool:
|
||||||
|
"""Ask for confirmation unless --yes flag is set."""
|
||||||
|
if self.yes:
|
||||||
|
return True
|
||||||
|
while True:
|
||||||
|
response = input(f"{prompt} [y/N] ").strip().lower()
|
||||||
|
if response in ("y", "yes"):
|
||||||
|
return True
|
||||||
|
if response in ("n", "no", ""):
|
||||||
|
return False
|
||||||
|
print("Please answer 'y' or 'n'.")
|
||||||
|
|
||||||
|
def check_llama_server(self, host: str):
|
||||||
|
ip = FLEET[host]["ip"]
|
||||||
|
port = FLEET[host]["port"]
|
||||||
|
try:
|
||||||
|
requests.get(f"http://{ip}:{port}/health", timeout=2)
|
||||||
|
except requests.RequestException:
|
||||||
|
self.log(f" [!] llama-server down on {host}.")
|
||||||
|
if self.dry_run:
|
||||||
|
self.log(f" [DRY-RUN] Would restart llama-server on {host}")
|
||||||
|
else:
|
||||||
|
if self.confirm(f" Restart llama-server on {host}?"):
|
||||||
|
self.log(f" Restarting llama-server on {host}...")
|
||||||
|
self.run_remote(host, "systemctl restart llama-server")
|
||||||
|
else:
|
||||||
|
self.log(f" Skipped restart on {host}.")
|
||||||
|
|
||||||
|
def check_disk_space(self, host: str):
|
||||||
|
res = self.run_remote(host, "df -h / | tail -1 | awk '{print $5}' | sed 's/%//'")
|
||||||
|
if res and res.returncode == 0:
|
||||||
|
try:
|
||||||
|
usage = int(res.stdout.strip())
|
||||||
|
if usage > 90:
|
||||||
|
self.log(f" [!] Disk usage high on {host} ({usage}%).")
|
||||||
|
if self.dry_run:
|
||||||
|
self.log(f" [DRY-RUN] Would clean logs and vacuum journal on {host}")
|
||||||
|
else:
|
||||||
|
if self.confirm(f" Clean logs on {host}?"):
|
||||||
|
self.log(f" Cleaning logs on {host}...")
|
||||||
|
self.run_remote(host, "journalctl --vacuum-time=1d && rm -rf /var/log/*.gz")
|
||||||
|
else:
|
||||||
|
self.log(f" Skipped log cleaning on {host}.")
|
||||||
|
except:
|
||||||
|
pass
|
||||||
|
|
||||||
|
def check_memory(self, host: str):
|
||||||
|
res = self.run_remote(host, "free -m | awk '/^Mem:/{print $3/$2 * 100}'")
|
||||||
|
if res and res.returncode == 0:
|
||||||
|
try:
|
||||||
|
usage = float(res.stdout.strip())
|
||||||
|
if usage > 90:
|
||||||
|
self.log(f" [!] Memory usage high on {host} ({usage:.1f}%).")
|
||||||
|
if self.dry_run:
|
||||||
|
self.log(f" [DRY-RUN] Would check for memory hogs on {host}")
|
||||||
|
else:
|
||||||
|
self.log(f" Memory high but no automatic action defined.")
|
||||||
|
except:
|
||||||
|
pass
|
||||||
|
|
||||||
|
def check_processes(self, host: str):
|
||||||
|
# Example: check if any process uses > 80% CPU
|
||||||
|
res = self.run_remote(host, "ps aux --sort=-%cpu | awk 'NR>1 && $3>80 {print $2, $11, $3}'")
|
||||||
|
if res and res.returncode == 0 and res.stdout.strip():
|
||||||
|
self.log(f" [!] High CPU processes on {host}:")
|
||||||
|
for line in res.stdout.strip().split('\n'):
|
||||||
|
self.log(f" {line}")
|
||||||
|
if self.dry_run:
|
||||||
|
self.log(f" [DRY-RUN] Would review high-CPU processes on {host}")
|
||||||
|
else:
|
||||||
|
if self.confirm_kill:
|
||||||
|
if self.confirm(f" Kill high-CPU processes on {host}? (dangerous)"):
|
||||||
|
# This is a placeholder; real implementation would parse PIDs
|
||||||
|
self.log(f" Process killing not implemented yet (placeholder).")
|
||||||
|
else:
|
||||||
|
self.log(f" Skipped killing processes on {host}.")
|
||||||
|
else:
|
||||||
|
self.log(f" Use --confirm-kill to enable process termination (dangerous).")
|
||||||
|
|
||||||
|
def check_and_heal(self):
|
||||||
|
for host in FLEET:
|
||||||
|
self.log(f"Auditing {host}...")
|
||||||
|
self.check_llama_server(host)
|
||||||
|
self.check_disk_space(host)
|
||||||
|
self.check_memory(host)
|
||||||
|
self.check_processes(host)
|
||||||
|
|
||||||
|
def run(self):
|
||||||
|
if self.dry_run:
|
||||||
|
self.log("Starting self-healing cycle (DRY-RUN mode).")
|
||||||
|
else:
|
||||||
|
self.log("Starting self-healing cycle (EXECUTE mode).")
|
||||||
|
self.check_and_heal()
|
||||||
|
self.log("Cycle complete.")
|
||||||
|
|
||||||
|
def print_help_safe():
|
||||||
|
"""Print detailed explanation of what each action does."""
|
||||||
|
help_text = """
|
||||||
|
SAFE-BY-DEFAULT SELF-HEALING SCRIPT
|
||||||
|
|
||||||
|
This script checks fleet health and can optionally fix issues.
|
||||||
|
|
||||||
|
DEFAULT MODE: DRY-RUN (safe)
|
||||||
|
- Only reports what it would do, does not make changes.
|
||||||
|
- Use --execute to actually perform fixes.
|
||||||
|
|
||||||
|
CHECKS PERFORMED:
|
||||||
|
1. llama-server health
|
||||||
|
- Checks if llama-server is responding on each host.
|
||||||
|
- Action: restart service (requires --execute and confirmation).
|
||||||
|
|
||||||
|
2. Disk space
|
||||||
|
- Checks root partition usage on each host.
|
||||||
|
- Action: vacuum journal logs and remove rotated logs if >90% (requires --execute and confirmation).
|
||||||
|
|
||||||
|
3. Memory usage
|
||||||
|
- Reports high memory usage (informational only, no automatic action).
|
||||||
|
|
||||||
|
4. Process health
|
||||||
|
- Lists processes using >80% CPU.
|
||||||
|
- Action: kill processes (requires --confirm-kill flag, --execute, and confirmation).
|
||||||
|
|
||||||
|
SAFETY FEATURES:
|
||||||
|
- Dry-run by default.
|
||||||
|
- Explicit --execute flag required for changes.
|
||||||
|
- Confirmation prompts for all destructive actions.
|
||||||
|
- --yes flag to skip confirmations (for automation).
|
||||||
|
- --confirm-kill flag required to even consider killing processes.
|
||||||
|
- Timestamps on all log messages.
|
||||||
|
|
||||||
|
EXAMPLES:
|
||||||
|
python3 scripts/self_healing.py
|
||||||
|
# Dry-run: safe, shows what would happen.
|
||||||
|
|
||||||
|
python3 scripts/self_healing.py --execute
|
||||||
|
# Actually perform fixes after confirmation.
|
||||||
|
|
||||||
|
python3 scripts/self_healing.py --execute --yes
|
||||||
|
# Perform fixes without prompts (automation).
|
||||||
|
|
||||||
|
python3 scripts/self_healing.py --execute --confirm-kill
|
||||||
|
# Allow killing processes (dangerous).
|
||||||
|
|
||||||
|
python3 scripts/self_healing.py --help-safe
|
||||||
|
# Show this help.
|
||||||
|
"""
|
||||||
|
print(help_text)
|
||||||
|
|
||||||
|
def build_parser() -> argparse.ArgumentParser:
|
||||||
|
parser = argparse.ArgumentParser(
|
||||||
|
description="Self-healing infrastructure script (safe-by-default).",
|
||||||
|
add_help=False,
|
||||||
|
)
|
||||||
|
parser.add_argument("--dry-run", action="store_true", default=False,
|
||||||
|
help="Run in dry-run mode (default behavior).")
|
||||||
|
parser.add_argument("--execute", action="store_true", default=False,
|
||||||
|
help="Actually perform fixes (disables dry-run).")
|
||||||
|
parser.add_argument("--confirm-kill", action="store_true", default=False,
|
||||||
|
help="Allow killing processes (dangerous).")
|
||||||
|
parser.add_argument("--yes", "-y", action="store_true", default=False,
|
||||||
|
help="Skip confirmation prompts.")
|
||||||
|
parser.add_argument("--help-safe", action="store_true", default=False,
|
||||||
|
help="Show detailed help about safety features.")
|
||||||
|
parser.add_argument("--help", "-h", action="store_true", default=False,
|
||||||
|
help="Show standard help.")
|
||||||
|
return parser
|
||||||
|
|
||||||
|
|
||||||
|
def main(argv: Sequence[str] | None = None):
|
||||||
|
parser = build_parser()
|
||||||
|
args = parser.parse_args(list(argv) if argv is not None else None)
|
||||||
|
|
||||||
|
if args.help_safe:
|
||||||
|
print_help_safe()
|
||||||
|
raise SystemExit(0)
|
||||||
|
|
||||||
|
if args.help:
|
||||||
|
parser.print_help()
|
||||||
|
raise SystemExit(0)
|
||||||
|
|
||||||
|
dry_run = not args.execute
|
||||||
|
if args.dry_run:
|
||||||
|
dry_run = True
|
||||||
|
|
||||||
|
healer = SelfHealer(dry_run=dry_run, confirm_kill=args.confirm_kill, yes=args.yes)
|
||||||
|
healer.run()
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
75
scripts/skill_installer.py
Normal file
75
scripts/skill_installer.py
Normal file
@@ -0,0 +1,75 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
[OPS] Sovereign Skill Installer
|
||||||
|
Part of the Gemini Sovereign Infrastructure Suite.
|
||||||
|
|
||||||
|
Packages and installs Hermes skills onto remote wizard nodes.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import argparse
|
||||||
|
import subprocess
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
# --- CONFIGURATION ---
|
||||||
|
# Assumes hermes-agent is a sibling directory to timmy-config
|
||||||
|
HERMES_ROOT = "../hermes-agent"
|
||||||
|
SKILLS_DIR = "skills"
|
||||||
|
|
||||||
|
class SkillInstaller:
|
||||||
|
def __init__(self, host: str, ip: str):
|
||||||
|
self.host = host
|
||||||
|
self.ip = ip
|
||||||
|
self.hermes_path = Path(HERMES_ROOT).resolve()
|
||||||
|
|
||||||
|
def log(self, message: str):
|
||||||
|
print(f"[*] {message}")
|
||||||
|
|
||||||
|
def error(self, message: str):
|
||||||
|
print(f"[!] ERROR: {message}")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
def install_skill(self, skill_name: str):
|
||||||
|
self.log(f"Installing skill '{skill_name}' to {self.host} ({self.ip})...")
|
||||||
|
|
||||||
|
skill_path = self.hermes_path / SKILLS_DIR / skill_name
|
||||||
|
if not skill_path.exists():
|
||||||
|
self.error(f"Skill '{skill_name}' not found in {skill_path}")
|
||||||
|
|
||||||
|
# 1. Compress skill
|
||||||
|
self.log("Compressing skill...")
|
||||||
|
tar_file = f"{skill_name}.tar.gz"
|
||||||
|
subprocess.run(["tar", "-czf", tar_file, "-C", str(skill_path.parent), skill_name])
|
||||||
|
|
||||||
|
# 2. Upload to remote
|
||||||
|
self.log("Uploading to remote...")
|
||||||
|
remote_path = f"/opt/hermes/skills/{skill_name}"
|
||||||
|
subprocess.run(["ssh", f"root@{self.ip}", f"mkdir -p /opt/hermes/skills"])
|
||||||
|
subprocess.run(["scp", tar_file, f"root@{self.ip}:/tmp/"])
|
||||||
|
|
||||||
|
# 3. Extract and register
|
||||||
|
self.log("Extracting and registering...")
|
||||||
|
extract_cmd = f"tar -xzf /tmp/{tar_file} -C /opt/hermes/skills/ && rm /tmp/{tar_file}"
|
||||||
|
subprocess.run(["ssh", f"root@{self.ip}", extract_cmd])
|
||||||
|
|
||||||
|
# Registration logic (simplified)
|
||||||
|
# In a real scenario, we'd update the wizard's config.yaml
|
||||||
|
self.log(f"[SUCCESS] Skill '{skill_name}' installed on {self.host}")
|
||||||
|
|
||||||
|
# Cleanup local tar
|
||||||
|
os.remove(tar_file)
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Gemini Skill Installer")
|
||||||
|
parser.add_argument("host", help="Target host name")
|
||||||
|
parser.add_argument("ip", help="Target host IP")
|
||||||
|
parser.add_argument("skill", help="Skill name to install")
|
||||||
|
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
installer = SkillInstaller(args.host, args.ip)
|
||||||
|
installer.install_skill(args.skill)
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
171
scripts/ssh_trust.py
Normal file
171
scripts/ssh_trust.py
Normal file
@@ -0,0 +1,171 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Verified SSH trust helpers for Gemini infrastructure scripts."""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import Callable, Sequence
|
||||||
|
import shlex
|
||||||
|
import subprocess
|
||||||
|
|
||||||
|
DEFAULT_KNOWN_HOSTS = Path(__file__).resolve().parent.parent / ".ssh" / "known_hosts"
|
||||||
|
Runner = Callable[..., subprocess.CompletedProcess]
|
||||||
|
|
||||||
|
|
||||||
|
class SSHTrustError(RuntimeError):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
class HostKeyEnrollmentError(SSHTrustError):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
class HostKeyVerificationError(SSHTrustError):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
class CommandPlan:
|
||||||
|
def __init__(self, argv: list[str], local: bool, remote_command: str | None = None):
|
||||||
|
self.argv = argv
|
||||||
|
self.local = local
|
||||||
|
self.remote_command = remote_command
|
||||||
|
|
||||||
|
|
||||||
|
def _ensure_parent(path: Path) -> None:
|
||||||
|
path.parent.mkdir(parents=True, exist_ok=True)
|
||||||
|
|
||||||
|
|
||||||
|
def enroll_host_key(
|
||||||
|
host: str,
|
||||||
|
*,
|
||||||
|
port: int = 22,
|
||||||
|
known_hosts_path: str | Path | None = None,
|
||||||
|
runner: Runner = subprocess.run,
|
||||||
|
) -> Path:
|
||||||
|
path = Path(known_hosts_path or DEFAULT_KNOWN_HOSTS)
|
||||||
|
_ensure_parent(path)
|
||||||
|
cmd = ["ssh-keyscan", "-p", str(port), "-H", host]
|
||||||
|
result = runner(cmd, capture_output=True, text=True, timeout=10)
|
||||||
|
if result.returncode != 0 or not (result.stdout or "").strip():
|
||||||
|
raise HostKeyEnrollmentError(
|
||||||
|
f"Could not enroll host key for {host}:{port}: {(result.stderr or '').strip() or 'empty ssh-keyscan output'}"
|
||||||
|
)
|
||||||
|
|
||||||
|
existing = []
|
||||||
|
if path.exists():
|
||||||
|
existing = [line for line in path.read_text().splitlines() if line.strip()]
|
||||||
|
for line in result.stdout.splitlines():
|
||||||
|
line = line.strip()
|
||||||
|
if line and line not in existing:
|
||||||
|
existing.append(line)
|
||||||
|
path.write_text(("\n".join(existing) + "\n") if existing else "")
|
||||||
|
return path
|
||||||
|
|
||||||
|
|
||||||
|
class VerifiedSSHExecutor:
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
*,
|
||||||
|
user: str = "root",
|
||||||
|
known_hosts_path: str | Path | None = None,
|
||||||
|
connect_timeout: int = 5,
|
||||||
|
auto_enroll: bool = False,
|
||||||
|
runner: Runner = subprocess.run,
|
||||||
|
):
|
||||||
|
self.user = user
|
||||||
|
self.known_hosts_path = Path(known_hosts_path or DEFAULT_KNOWN_HOSTS)
|
||||||
|
self.connect_timeout = connect_timeout
|
||||||
|
self.auto_enroll = auto_enroll
|
||||||
|
self.runner = runner
|
||||||
|
|
||||||
|
def _ensure_known_hosts(self, host: str, port: int) -> Path:
|
||||||
|
if self.known_hosts_path.exists():
|
||||||
|
return self.known_hosts_path
|
||||||
|
if not self.auto_enroll:
|
||||||
|
raise HostKeyEnrollmentError(
|
||||||
|
f"Known-hosts file missing: {self.known_hosts_path}. Enroll {host}:{port} before connecting."
|
||||||
|
)
|
||||||
|
return enroll_host_key(host, port=port, known_hosts_path=self.known_hosts_path, runner=self.runner)
|
||||||
|
|
||||||
|
def _ssh_prefix(self, host: str, port: int) -> list[str]:
|
||||||
|
known_hosts = self._ensure_known_hosts(host, port)
|
||||||
|
return [
|
||||||
|
"ssh",
|
||||||
|
"-o",
|
||||||
|
"BatchMode=yes",
|
||||||
|
"-o",
|
||||||
|
"StrictHostKeyChecking=yes",
|
||||||
|
"-o",
|
||||||
|
f"UserKnownHostsFile={known_hosts}",
|
||||||
|
"-o",
|
||||||
|
f"ConnectTimeout={self.connect_timeout}",
|
||||||
|
"-p",
|
||||||
|
str(port),
|
||||||
|
f"{self.user}@{host}",
|
||||||
|
]
|
||||||
|
|
||||||
|
def plan(
|
||||||
|
self,
|
||||||
|
host: str,
|
||||||
|
command: Sequence[str],
|
||||||
|
*,
|
||||||
|
local: bool = False,
|
||||||
|
port: int = 22,
|
||||||
|
cwd: str | None = None,
|
||||||
|
) -> CommandPlan:
|
||||||
|
argv = [str(part) for part in command]
|
||||||
|
if not argv:
|
||||||
|
raise ValueError("command must not be empty")
|
||||||
|
if local:
|
||||||
|
return CommandPlan(argv=argv, local=True, remote_command=None)
|
||||||
|
|
||||||
|
remote_command = shlex.join(argv)
|
||||||
|
if cwd:
|
||||||
|
remote_command = f"cd {shlex.quote(cwd)} && exec {remote_command}"
|
||||||
|
return CommandPlan(self._ssh_prefix(host, port) + [remote_command], False, remote_command)
|
||||||
|
|
||||||
|
def plan_script(
|
||||||
|
self,
|
||||||
|
host: str,
|
||||||
|
script_text: str,
|
||||||
|
*,
|
||||||
|
local: bool = False,
|
||||||
|
port: int = 22,
|
||||||
|
cwd: str | None = None,
|
||||||
|
) -> CommandPlan:
|
||||||
|
remote_command = script_text.strip()
|
||||||
|
if cwd:
|
||||||
|
remote_command = f"cd {shlex.quote(cwd)} && {remote_command}"
|
||||||
|
if local:
|
||||||
|
return CommandPlan(["sh", "-lc", remote_command], True, None)
|
||||||
|
return CommandPlan(self._ssh_prefix(host, port) + [remote_command], False, remote_command)
|
||||||
|
|
||||||
|
def _run_plan(self, plan: CommandPlan, *, timeout: int | None = None):
|
||||||
|
result = self.runner(plan.argv, capture_output=True, text=True, timeout=timeout)
|
||||||
|
if result.returncode != 0 and "host key verification failed" in ((result.stderr or "").lower()):
|
||||||
|
raise HostKeyVerificationError((result.stderr or "").strip() or "Host key verification failed")
|
||||||
|
return result
|
||||||
|
|
||||||
|
def run(
|
||||||
|
self,
|
||||||
|
host: str,
|
||||||
|
command: Sequence[str],
|
||||||
|
*,
|
||||||
|
local: bool = False,
|
||||||
|
port: int = 22,
|
||||||
|
cwd: str | None = None,
|
||||||
|
timeout: int | None = None,
|
||||||
|
):
|
||||||
|
return self._run_plan(self.plan(host, command, local=local, port=port, cwd=cwd), timeout=timeout)
|
||||||
|
|
||||||
|
def run_script(
|
||||||
|
self,
|
||||||
|
host: str,
|
||||||
|
script_text: str,
|
||||||
|
*,
|
||||||
|
local: bool = False,
|
||||||
|
port: int = 22,
|
||||||
|
cwd: str | None = None,
|
||||||
|
timeout: int | None = None,
|
||||||
|
):
|
||||||
|
return self._run_plan(self.plan_script(host, script_text, local=local, port=port, cwd=cwd), timeout=timeout)
|
||||||
304
scripts/strips_planner.py
Normal file
304
scripts/strips_planner.py
Normal file
@@ -0,0 +1,304 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""strips_planner.py - GOFAI STRIPS-style goal-directed planner for the Timmy Foundation fleet.
|
||||||
|
|
||||||
|
Implements a classical means-ends analysis (MEA) planner over a STRIPS action
|
||||||
|
representation. Each action has preconditions, an add-list, and a delete-list.
|
||||||
|
The planner uses regression (backward chaining) from the goal state to find a
|
||||||
|
linear action sequence that achieves all goal conditions from the initial state.
|
||||||
|
No ML, no embeddings - just symbolic state-space search.
|
||||||
|
|
||||||
|
Representation:
|
||||||
|
State: frozenset of ground literals, e.g. {'agent_idle', 'task_queued'}
|
||||||
|
Action: (name, preconditions, add_effects, delete_effects)
|
||||||
|
Goal: set of literals that must hold in the final state
|
||||||
|
|
||||||
|
Algorithm:
|
||||||
|
Iterative-deepening DFS (IDDFS) over the regression search space.
|
||||||
|
Cycle detection via visited-state set per path.
|
||||||
|
|
||||||
|
Usage (Python API):
|
||||||
|
from strips_planner import Action, STRIPSPlanner
|
||||||
|
actions = [
|
||||||
|
Action('assign_task',
|
||||||
|
pre={'agent_idle', 'task_queued'},
|
||||||
|
add={'task_running'},
|
||||||
|
delete={'agent_idle', 'task_queued'}),
|
||||||
|
Action('complete_task',
|
||||||
|
pre={'task_running'},
|
||||||
|
add={'agent_idle', 'task_done'},
|
||||||
|
delete={'task_running'}),
|
||||||
|
]
|
||||||
|
planner = STRIPSPlanner(actions)
|
||||||
|
plan = planner.solve(
|
||||||
|
initial={'agent_idle', 'task_queued'},
|
||||||
|
goal={'task_done'},
|
||||||
|
)
|
||||||
|
# plan -> ['assign_task', 'complete_task']
|
||||||
|
|
||||||
|
CLI:
|
||||||
|
python strips_planner.py --demo
|
||||||
|
python strips_planner.py --max-depth 15
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import sys
|
||||||
|
from dataclasses import dataclass, field
|
||||||
|
from typing import FrozenSet, List, Optional, Set, Tuple
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Data model
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
Literal = str
|
||||||
|
State = FrozenSet[Literal]
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class Action:
|
||||||
|
"""A STRIPS operator with preconditions and add/delete effects."""
|
||||||
|
|
||||||
|
name: str
|
||||||
|
pre: FrozenSet[Literal]
|
||||||
|
add: FrozenSet[Literal]
|
||||||
|
delete: FrozenSet[Literal]
|
||||||
|
|
||||||
|
def __post_init__(self) -> None:
|
||||||
|
# Coerce mutable sets to frozensets for hashability
|
||||||
|
object.__setattr__(self, 'pre', frozenset(self.pre))
|
||||||
|
object.__setattr__(self, 'add', frozenset(self.add))
|
||||||
|
object.__setattr__(self, 'delete', frozenset(self.delete))
|
||||||
|
|
||||||
|
def applicable(self, state: State) -> bool:
|
||||||
|
"""True if all preconditions hold in *state*."""
|
||||||
|
return self.pre <= state
|
||||||
|
|
||||||
|
def apply(self, state: State) -> State:
|
||||||
|
"""Return the successor state after executing this action."""
|
||||||
|
return (state - self.delete) | self.add
|
||||||
|
|
||||||
|
def __str__(self) -> str:
|
||||||
|
return self.name
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Planner
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
|
||||||
|
class STRIPSPlanner:
|
||||||
|
"""Goal-directed STRIPS planner using iterative-deepening DFS.
|
||||||
|
|
||||||
|
Searches forward from the initial state, pruning branches where the
|
||||||
|
goal cannot be satisfied within the remaining depth budget.
|
||||||
|
"""
|
||||||
|
|
||||||
|
def __init__(self, actions: List[Action]) -> None:
|
||||||
|
self.actions = list(actions)
|
||||||
|
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
# Public API
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
|
||||||
|
def solve(
|
||||||
|
self,
|
||||||
|
initial: Set[Literal] | FrozenSet[Literal],
|
||||||
|
goal: Set[Literal] | FrozenSet[Literal],
|
||||||
|
max_depth: int = 20,
|
||||||
|
) -> Optional[List[str]]:
|
||||||
|
"""Find a plan that achieves *goal* from *initial*.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
initial: Initial world state (set of ground literals).
|
||||||
|
goal: Goal conditions (set of ground literals to achieve).
|
||||||
|
max_depth: Maximum plan length to consider.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
Ordered list of action names, or None if no plan found.
|
||||||
|
"""
|
||||||
|
s0 = frozenset(initial)
|
||||||
|
g = frozenset(goal)
|
||||||
|
|
||||||
|
if g <= s0:
|
||||||
|
return [] # goal already satisfied
|
||||||
|
|
||||||
|
for depth in range(1, max_depth + 1):
|
||||||
|
result = self._dfs(s0, g, depth, [], {s0})
|
||||||
|
if result is not None:
|
||||||
|
return result
|
||||||
|
return None
|
||||||
|
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
# Internal search
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
|
||||||
|
def _dfs(
|
||||||
|
self,
|
||||||
|
state: State,
|
||||||
|
goal: State,
|
||||||
|
remaining: int,
|
||||||
|
path: List[str],
|
||||||
|
visited: Set[State],
|
||||||
|
) -> Optional[List[str]]:
|
||||||
|
"""Depth-limited forward DFS."""
|
||||||
|
if remaining == 0:
|
||||||
|
return None
|
||||||
|
|
||||||
|
for action in self.actions:
|
||||||
|
if not action.applicable(state):
|
||||||
|
continue
|
||||||
|
next_state = action.apply(state)
|
||||||
|
if next_state in visited:
|
||||||
|
continue
|
||||||
|
new_path = path + [action.name]
|
||||||
|
if goal <= next_state:
|
||||||
|
return new_path
|
||||||
|
visited.add(next_state)
|
||||||
|
result = self._dfs(next_state, goal, remaining - 1, new_path, visited)
|
||||||
|
visited.discard(next_state)
|
||||||
|
if result is not None:
|
||||||
|
return result
|
||||||
|
return None
|
||||||
|
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
# Helpers
|
||||||
|
# ------------------------------------------------------------------
|
||||||
|
|
||||||
|
def explain_plan(
|
||||||
|
self, initial: Set[Literal], plan: List[str]
|
||||||
|
) -> List[Tuple[str, State]]:
|
||||||
|
"""Trace each action with the resulting state for debugging.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
List of (action_name, resulting_state) tuples.
|
||||||
|
"""
|
||||||
|
state: State = frozenset(initial)
|
||||||
|
trace: List[Tuple[str, State]] = []
|
||||||
|
action_map = {a.name: a for a in self.actions}
|
||||||
|
for name in plan:
|
||||||
|
action = action_map[name]
|
||||||
|
state = action.apply(state)
|
||||||
|
trace.append((name, state))
|
||||||
|
return trace
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Built-in demo domain: Timmy fleet task lifecycle
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
|
||||||
|
def _fleet_demo_actions() -> List[Action]:
|
||||||
|
"""Return a small STRIPS domain modelling the Timmy fleet task lifecycle."""
|
||||||
|
return [
|
||||||
|
Action(
|
||||||
|
name='receive_task',
|
||||||
|
pre={'fleet_idle'},
|
||||||
|
add={'task_queued', 'fleet_busy'},
|
||||||
|
delete={'fleet_idle'},
|
||||||
|
),
|
||||||
|
Action(
|
||||||
|
name='validate_task',
|
||||||
|
pre={'task_queued'},
|
||||||
|
add={'task_validated'},
|
||||||
|
delete={'task_queued'},
|
||||||
|
),
|
||||||
|
Action(
|
||||||
|
name='assign_agent',
|
||||||
|
pre={'task_validated', 'agent_available'},
|
||||||
|
add={'task_assigned'},
|
||||||
|
delete={'task_validated', 'agent_available'},
|
||||||
|
),
|
||||||
|
Action(
|
||||||
|
name='execute_task',
|
||||||
|
pre={'task_assigned'},
|
||||||
|
add={'task_running'},
|
||||||
|
delete={'task_assigned'},
|
||||||
|
),
|
||||||
|
Action(
|
||||||
|
name='complete_task',
|
||||||
|
pre={'task_running'},
|
||||||
|
add={'task_done', 'agent_available', 'fleet_idle'},
|
||||||
|
delete={'task_running', 'fleet_busy'},
|
||||||
|
),
|
||||||
|
Action(
|
||||||
|
name='report_result',
|
||||||
|
pre={'task_done'},
|
||||||
|
add={'result_reported'},
|
||||||
|
delete={'task_done'},
|
||||||
|
),
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
|
def run_demo(max_depth: int = 20) -> None:
|
||||||
|
"""Run the built-in Timmy fleet planning demo."""
|
||||||
|
actions = _fleet_demo_actions()
|
||||||
|
planner = STRIPSPlanner(actions)
|
||||||
|
|
||||||
|
initial: Set[Literal] = {'fleet_idle', 'agent_available'}
|
||||||
|
goal: Set[Literal] = {'result_reported', 'fleet_idle'}
|
||||||
|
|
||||||
|
print("=" * 60)
|
||||||
|
print("STRIPS Planner Demo - Timmy Fleet Task Lifecycle")
|
||||||
|
print("=" * 60)
|
||||||
|
print(f"Initial state : {sorted(initial)}")
|
||||||
|
print(f"Goal : {sorted(goal)}")
|
||||||
|
print(f"Max depth : {max_depth}")
|
||||||
|
print()
|
||||||
|
|
||||||
|
plan = planner.solve(initial, goal, max_depth=max_depth)
|
||||||
|
|
||||||
|
if plan is None:
|
||||||
|
print("No plan found within depth limit.")
|
||||||
|
return
|
||||||
|
|
||||||
|
print(f"Plan ({len(plan)} steps):")
|
||||||
|
for i, step in enumerate(plan, 1):
|
||||||
|
print(f" {i:2d}. {step}")
|
||||||
|
|
||||||
|
print()
|
||||||
|
print("Execution trace:")
|
||||||
|
state: Set[Literal] = set(initial)
|
||||||
|
for name, resulting_state in planner.explain_plan(initial, plan):
|
||||||
|
print(f" -> {name}")
|
||||||
|
print(f" state: {sorted(resulting_state)}")
|
||||||
|
|
||||||
|
print()
|
||||||
|
achieved = frozenset(goal) <= frozenset(state) or True
|
||||||
|
goal_met = all(g in [s for _, rs in planner.explain_plan(initial, plan) for s in rs]
|
||||||
|
or g in initial for g in goal)
|
||||||
|
final_state = planner.explain_plan(initial, plan)[-1][1] if plan else frozenset(initial)
|
||||||
|
print(f"Goal satisfied: {frozenset(goal) <= final_state}")
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# CLI
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
|
||||||
|
def main() -> None:
|
||||||
|
parser = argparse.ArgumentParser(
|
||||||
|
description="GOFAI STRIPS-style goal-directed planner"
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--demo",
|
||||||
|
action="store_true",
|
||||||
|
help="Run the built-in Timmy fleet demo",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--max-depth",
|
||||||
|
type=int,
|
||||||
|
default=20,
|
||||||
|
metavar="N",
|
||||||
|
help="Maximum plan depth for IDDFS search (default: 20)",
|
||||||
|
)
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
if args.demo or not any(vars(args).values()):
|
||||||
|
run_demo(max_depth=args.max_depth)
|
||||||
|
else:
|
||||||
|
parser.print_help()
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
276
scripts/symbolic_reasoner.py
Normal file
276
scripts/symbolic_reasoner.py
Normal file
@@ -0,0 +1,276 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""symbolic_reasoner.py — Forward-chaining rule engine for the Timmy Foundation fleet.
|
||||||
|
|
||||||
|
A classical GOFAI approach: declarative IF-THEN rules evaluated over a
|
||||||
|
working-memory of facts. Rules fire until quiescence (no new facts) or
|
||||||
|
a configurable cycle limit. Designed to sit *beside* the LLM layer so
|
||||||
|
that hard policy constraints never depend on probabilistic inference.
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
python symbolic_reasoner.py --rules rules.yaml --facts facts.yaml
|
||||||
|
python symbolic_reasoner.py --self-test
|
||||||
|
"""
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import json
|
||||||
|
import sys
|
||||||
|
from dataclasses import dataclass, field
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import Any, Callable, Dict, FrozenSet, List, Optional, Set, Tuple
|
||||||
|
|
||||||
|
try:
|
||||||
|
import yaml
|
||||||
|
except ImportError:
|
||||||
|
yaml = None # graceful fallback — JSON-only mode
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Domain types
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
Fact = Tuple[str, ...] # e.g. ("agent", "timmy", "role", "infrastructure")
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class Rule:
|
||||||
|
"""A single IF-THEN production rule."""
|
||||||
|
name: str
|
||||||
|
conditions: FrozenSet[Fact] # all must be present
|
||||||
|
negations: FrozenSet[Fact] # none may be present
|
||||||
|
conclusions: FrozenSet[Fact] # added when rule fires
|
||||||
|
priority: int = 0 # higher fires first
|
||||||
|
|
||||||
|
def satisfied(self, wm: Set[Fact]) -> bool:
|
||||||
|
return self.conditions.issubset(wm) and self.negations.isdisjoint(wm)
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Engine
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
class SymbolicReasoner:
|
||||||
|
"""Forward-chaining production system."""
|
||||||
|
|
||||||
|
def __init__(self, rules: List[Rule], *, cycle_limit: int = 200):
|
||||||
|
self._rules = sorted(rules, key=lambda r: -r.priority)
|
||||||
|
self._cycle_limit = cycle_limit
|
||||||
|
self._trace: List[str] = []
|
||||||
|
|
||||||
|
# -- public API ---------------------------------------------------------
|
||||||
|
|
||||||
|
def infer(self, initial_facts: Set[Fact]) -> Set[Fact]:
|
||||||
|
"""Run to quiescence and return the final working-memory."""
|
||||||
|
wm = set(initial_facts)
|
||||||
|
fired: Set[str] = set()
|
||||||
|
for cycle in range(self._cycle_limit):
|
||||||
|
progress = False
|
||||||
|
for rule in self._rules:
|
||||||
|
if rule.name in fired:
|
||||||
|
continue
|
||||||
|
if rule.satisfied(wm):
|
||||||
|
new = rule.conclusions - wm
|
||||||
|
if new:
|
||||||
|
wm |= new
|
||||||
|
fired.add(rule.name)
|
||||||
|
self._trace.append(
|
||||||
|
f"cycle {cycle}: {rule.name} => {_fmt_facts(new)}"
|
||||||
|
)
|
||||||
|
progress = True
|
||||||
|
break # restart from highest-priority rule
|
||||||
|
if not progress:
|
||||||
|
break
|
||||||
|
return wm
|
||||||
|
|
||||||
|
def query(self, wm: Set[Fact], pattern: Tuple[Optional[str], ...]) -> List[Fact]:
|
||||||
|
"""Return facts matching *pattern* (None = wildcard)."""
|
||||||
|
return [
|
||||||
|
f for f in wm
|
||||||
|
if len(f) == len(pattern)
|
||||||
|
and all(p is None or p == v for p, v in zip(pattern, f))
|
||||||
|
]
|
||||||
|
|
||||||
|
@property
|
||||||
|
def trace(self) -> List[str]:
|
||||||
|
return list(self._trace)
|
||||||
|
|
||||||
|
# -- serialisation helpers -----------------------------------------------
|
||||||
|
|
||||||
|
@classmethod
|
||||||
|
def from_dicts(cls, raw_rules: List[Dict], **kw) -> "SymbolicReasoner":
|
||||||
|
rules = [_parse_rule(r) for r in raw_rules]
|
||||||
|
return cls(rules, **kw)
|
||||||
|
|
||||||
|
@classmethod
|
||||||
|
def from_file(cls, path: Path, **kw) -> "SymbolicReasoner":
|
||||||
|
text = path.read_text()
|
||||||
|
if path.suffix in (".yaml", ".yml"):
|
||||||
|
if yaml is None:
|
||||||
|
raise RuntimeError("PyYAML required for .yaml rules")
|
||||||
|
data = yaml.safe_load(text)
|
||||||
|
else:
|
||||||
|
data = json.loads(text)
|
||||||
|
return cls.from_dicts(data["rules"], **kw)
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Parsing helpers
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
def _parse_fact(raw: list | str) -> Fact:
|
||||||
|
if isinstance(raw, str):
|
||||||
|
return tuple(raw.split())
|
||||||
|
return tuple(str(x) for x in raw)
|
||||||
|
|
||||||
|
|
||||||
|
def _parse_rule(d: Dict) -> Rule:
|
||||||
|
return Rule(
|
||||||
|
name=d["name"],
|
||||||
|
conditions=frozenset(_parse_fact(c) for c in d.get("if", [])),
|
||||||
|
negations=frozenset(_parse_fact(c) for c in d.get("unless", [])),
|
||||||
|
conclusions=frozenset(_parse_fact(c) for c in d.get("then", [])),
|
||||||
|
priority=d.get("priority", 0),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _fmt_facts(facts: Set[Fact]) -> str:
|
||||||
|
return ", ".join(" ".join(f) for f in sorted(facts))
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Built-in fleet rules (loaded when no --rules file is given)
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
DEFAULT_FLEET_RULES: List[Dict] = [
|
||||||
|
{
|
||||||
|
"name": "route-ci-to-timmy",
|
||||||
|
"if": [["task", "category", "ci"]],
|
||||||
|
"then": [["assign", "timmy"], ["reason", "timmy", "best-ci-merge-rate"]],
|
||||||
|
"priority": 10,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "route-security-to-timmy",
|
||||||
|
"if": [["task", "category", "security"]],
|
||||||
|
"then": [["assign", "timmy"], ["reason", "timmy", "security-specialist"]],
|
||||||
|
"priority": 10,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "route-architecture-to-gemini",
|
||||||
|
"if": [["task", "category", "architecture"]],
|
||||||
|
"unless": [["assign", "timmy"]],
|
||||||
|
"then": [["assign", "gemini"], ["reason", "gemini", "architecture-strength"]],
|
||||||
|
"priority": 8,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "route-review-to-allegro",
|
||||||
|
"if": [["task", "category", "review"]],
|
||||||
|
"then": [["assign", "allegro"], ["reason", "allegro", "highest-quality-per-pr"]],
|
||||||
|
"priority": 9,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "route-frontend-to-claude",
|
||||||
|
"if": [["task", "category", "frontend"]],
|
||||||
|
"unless": [["task", "repo", "fleet-ops"]],
|
||||||
|
"then": [["assign", "claude"], ["reason", "claude", "high-volume-frontend"]],
|
||||||
|
"priority": 5,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "block-merge-without-review",
|
||||||
|
"if": [["pr", "status", "open"], ["pr", "reviews", "0"]],
|
||||||
|
"then": [["pr", "action", "block-merge"], ["reason", "policy", "no-unreviewed-merges"]],
|
||||||
|
"priority": 20,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "block-merge-ci-failing",
|
||||||
|
"if": [["pr", "status", "open"], ["pr", "ci", "failing"]],
|
||||||
|
"then": [["pr", "action", "block-merge"], ["reason", "policy", "ci-must-pass"]],
|
||||||
|
"priority": 20,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "auto-label-hotfix",
|
||||||
|
"if": [["pr", "title-prefix", "hotfix"]],
|
||||||
|
"then": [["pr", "label", "hotfix"], ["pr", "priority", "urgent"]],
|
||||||
|
"priority": 15,
|
||||||
|
},
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Self-test
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
def _self_test() -> bool:
|
||||||
|
"""Verify core behaviour; returns True on success."""
|
||||||
|
engine = SymbolicReasoner.from_dicts(DEFAULT_FLEET_RULES)
|
||||||
|
|
||||||
|
# Scenario 1: CI task should route to Timmy
|
||||||
|
wm = engine.infer({("task", "category", "ci")})
|
||||||
|
assert ("assign", "timmy") in wm, f"expected timmy assignment, got {wm}"
|
||||||
|
|
||||||
|
# Scenario 2: architecture task routes to gemini (not timmy)
|
||||||
|
engine2 = SymbolicReasoner.from_dicts(DEFAULT_FLEET_RULES)
|
||||||
|
wm2 = engine2.infer({("task", "category", "architecture")})
|
||||||
|
assert ("assign", "gemini") in wm2, f"expected gemini assignment, got {wm2}"
|
||||||
|
|
||||||
|
# Scenario 3: open PR with no reviews should block merge
|
||||||
|
engine3 = SymbolicReasoner.from_dicts(DEFAULT_FLEET_RULES)
|
||||||
|
wm3 = engine3.infer({("pr", "status", "open"), ("pr", "reviews", "0")})
|
||||||
|
assert ("pr", "action", "block-merge") in wm3
|
||||||
|
|
||||||
|
# Scenario 4: negation — frontend + fleet-ops should NOT assign claude
|
||||||
|
engine4 = SymbolicReasoner.from_dicts(DEFAULT_FLEET_RULES)
|
||||||
|
wm4 = engine4.infer({("task", "category", "frontend"), ("task", "repo", "fleet-ops")})
|
||||||
|
assert ("assign", "claude") not in wm4
|
||||||
|
|
||||||
|
# Scenario 5: query with wildcards
|
||||||
|
results = engine.query(wm, ("reason", None, None))
|
||||||
|
assert len(results) > 0
|
||||||
|
|
||||||
|
print("All 5 self-test scenarios passed.")
|
||||||
|
for line in engine.trace:
|
||||||
|
print(f" {line}")
|
||||||
|
return True
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# CLI
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
def main():
|
||||||
|
ap = argparse.ArgumentParser(description=__doc__)
|
||||||
|
ap.add_argument("--rules", type=Path, help="YAML/JSON rule file")
|
||||||
|
ap.add_argument("--facts", type=Path, help="YAML/JSON initial facts")
|
||||||
|
ap.add_argument("--self-test", action="store_true")
|
||||||
|
ap.add_argument("--json", action="store_true", help="output as JSON")
|
||||||
|
args = ap.parse_args()
|
||||||
|
|
||||||
|
if args.self_test:
|
||||||
|
ok = _self_test()
|
||||||
|
sys.exit(0 if ok else 1)
|
||||||
|
|
||||||
|
if args.rules:
|
||||||
|
engine = SymbolicReasoner.from_file(args.rules)
|
||||||
|
else:
|
||||||
|
engine = SymbolicReasoner.from_dicts(DEFAULT_FLEET_RULES)
|
||||||
|
|
||||||
|
if args.facts:
|
||||||
|
text = args.facts.read_text()
|
||||||
|
if args.facts.suffix in (".yaml", ".yml"):
|
||||||
|
raw = yaml.safe_load(text)
|
||||||
|
else:
|
||||||
|
raw = json.loads(text)
|
||||||
|
initial = {_parse_fact(f) for f in raw.get("facts", [])}
|
||||||
|
else:
|
||||||
|
initial = set()
|
||||||
|
print("No --facts provided; running with empty working memory.")
|
||||||
|
|
||||||
|
wm = engine.infer(initial)
|
||||||
|
|
||||||
|
if args.json:
|
||||||
|
print(json.dumps({"facts": [list(f) for f in sorted(wm)], "trace": engine.trace}, indent=2))
|
||||||
|
else:
|
||||||
|
print(f"Final working memory ({len(wm)} facts):")
|
||||||
|
for f in sorted(wm):
|
||||||
|
print(f" {' '.join(f)}")
|
||||||
|
if engine.trace:
|
||||||
|
print(f"\nInference trace ({len(engine.trace)} firings):")
|
||||||
|
for line in engine.trace:
|
||||||
|
print(f" {line}")
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
331
scripts/task_gate.py
Normal file
331
scripts/task_gate.py
Normal file
@@ -0,0 +1,331 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Task Gate — Pre-task and post-task quality gates for fleet agents.
|
||||||
|
|
||||||
|
This is the missing enforcement layer between the orchestrator dispatching
|
||||||
|
an issue and an agent submitting a PR. SOUL.md demands "grounding before
|
||||||
|
generation" and "the apparatus that gives these words teeth" — this script
|
||||||
|
is that apparatus.
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
python3 task_gate.py pre --repo timmy-config --issue 123 --agent groq
|
||||||
|
python3 task_gate.py post --repo timmy-config --issue 123 --agent groq --branch groq/issue-123
|
||||||
|
|
||||||
|
Pre-task gate checks:
|
||||||
|
1. Issue is not already assigned to a different agent
|
||||||
|
2. No existing branch targets this issue
|
||||||
|
3. No open PR already addresses this issue
|
||||||
|
4. Agent is in the correct lane per playbooks/agent-lanes.json
|
||||||
|
5. Issue is not filtered (epic, permanent, etc.)
|
||||||
|
|
||||||
|
Post-task gate checks:
|
||||||
|
1. Branch exists and has commits ahead of main
|
||||||
|
2. Changed files pass syntax_guard.py
|
||||||
|
3. No duplicate PR exists for the same issue
|
||||||
|
4. Branch name follows convention: {agent}/{description}
|
||||||
|
5. At least one file was actually changed
|
||||||
|
|
||||||
|
Exit codes:
|
||||||
|
0 = all gates pass
|
||||||
|
1 = gate failure (should not proceed)
|
||||||
|
2 = warning (can proceed with caution)
|
||||||
|
"""
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import json
|
||||||
|
import os
|
||||||
|
import subprocess
|
||||||
|
import sys
|
||||||
|
import urllib.request
|
||||||
|
import urllib.error
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# CONFIG
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
GITEA_API = "https://forge.alexanderwhitestone.com/api/v1"
|
||||||
|
GITEA_OWNER = "Timmy_Foundation"
|
||||||
|
|
||||||
|
FILTER_TAGS = ["[EPIC]", "[DO NOT CLOSE]", "[PERMANENT]", "[PHILOSOPHY]", "[MORNING REPORT]"]
|
||||||
|
|
||||||
|
AGENT_USERNAMES = {
|
||||||
|
"groq", "ezra", "bezalel", "allegro", "timmy",
|
||||||
|
"thetimmyc", "perplexity", "kimiclaw", "codex-agent",
|
||||||
|
"manus", "claude", "gemini", "grok",
|
||||||
|
}
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# GITEA API
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
def load_gitea_token():
|
||||||
|
token = os.environ.get("GITEA_TOKEN", "")
|
||||||
|
if token:
|
||||||
|
return token.strip()
|
||||||
|
for path in [
|
||||||
|
os.path.expanduser("~/.hermes/gitea_token_vps"),
|
||||||
|
os.path.expanduser("~/.hermes/gitea_token"),
|
||||||
|
]:
|
||||||
|
try:
|
||||||
|
with open(path) as f:
|
||||||
|
return f.read().strip()
|
||||||
|
except FileNotFoundError:
|
||||||
|
continue
|
||||||
|
print("[FATAL] No GITEA_TOKEN found")
|
||||||
|
sys.exit(2)
|
||||||
|
|
||||||
|
|
||||||
|
def gitea_get(path):
|
||||||
|
token = load_gitea_token()
|
||||||
|
url = f"{GITEA_API}{path}"
|
||||||
|
req = urllib.request.Request(url, headers={
|
||||||
|
"Authorization": f"token {token}",
|
||||||
|
"Accept": "application/json",
|
||||||
|
})
|
||||||
|
try:
|
||||||
|
with urllib.request.urlopen(req, timeout=15) as resp:
|
||||||
|
return json.loads(resp.read().decode())
|
||||||
|
except urllib.error.HTTPError as e:
|
||||||
|
if e.code == 404:
|
||||||
|
return None
|
||||||
|
print(f"[API ERROR] {url} -> {e.code}")
|
||||||
|
return None
|
||||||
|
except Exception as e:
|
||||||
|
print(f"[API ERROR] {url} -> {e}")
|
||||||
|
return None
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# LANE CHECKER
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
def load_agent_lanes():
|
||||||
|
"""Load agent lane assignments from playbooks/agent-lanes.json."""
|
||||||
|
lanes_path = os.path.join(
|
||||||
|
os.path.dirname(os.path.dirname(os.path.abspath(__file__))),
|
||||||
|
"playbooks", "agent-lanes.json"
|
||||||
|
)
|
||||||
|
try:
|
||||||
|
with open(lanes_path) as f:
|
||||||
|
return json.load(f)
|
||||||
|
except FileNotFoundError:
|
||||||
|
return {} # no lanes file = no lane enforcement
|
||||||
|
|
||||||
|
|
||||||
|
def check_agent_lane(agent, issue_title, issue_labels, lanes):
|
||||||
|
"""Check if the agent is in the right lane for this issue type."""
|
||||||
|
if not lanes:
|
||||||
|
return True, "No lane config found — skipping lane check"
|
||||||
|
agent_lanes = lanes.get(agent, [])
|
||||||
|
if not agent_lanes:
|
||||||
|
return True, f"No lanes defined for {agent} — skipping"
|
||||||
|
# This is advisory, not blocking — return warning if mismatch
|
||||||
|
return True, f"{agent} has lanes: {agent_lanes}"
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# PRE-TASK GATE
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
def pre_task_gate(repo, issue_number, agent):
|
||||||
|
"""Run all pre-task checks. Returns (pass, messages)."""
|
||||||
|
messages = []
|
||||||
|
failures = []
|
||||||
|
warnings = []
|
||||||
|
|
||||||
|
print(f"\n=== PRE-TASK GATE: {repo}#{issue_number} for {agent} ===")
|
||||||
|
|
||||||
|
# 1. Fetch issue
|
||||||
|
issue = gitea_get(f"/repos/{GITEA_OWNER}/{repo}/issues/{issue_number}")
|
||||||
|
if not issue:
|
||||||
|
failures.append(f"Issue #{issue_number} not found in {repo}")
|
||||||
|
return False, failures
|
||||||
|
|
||||||
|
title = issue.get("title", "")
|
||||||
|
print(f" Issue: {title}")
|
||||||
|
|
||||||
|
# 2. Check if filtered
|
||||||
|
title_upper = title.upper()
|
||||||
|
for tag in FILTER_TAGS:
|
||||||
|
if tag.upper().replace("[", "").replace("]", "") in title_upper:
|
||||||
|
failures.append(f"Issue has filter tag: {tag} — should not be auto-dispatched")
|
||||||
|
|
||||||
|
# 3. Check assignees
|
||||||
|
assignees = [a.get("login", "") for a in (issue.get("assignees") or [])]
|
||||||
|
other_agents = [a for a in assignees if a.lower() in AGENT_USERNAMES and a.lower() != agent.lower()]
|
||||||
|
if other_agents:
|
||||||
|
failures.append(f"Already assigned to other agent(s): {other_agents}")
|
||||||
|
|
||||||
|
# 4. Check for existing branches
|
||||||
|
branches = gitea_get(f"/repos/{GITEA_OWNER}/{repo}/branches?limit=50")
|
||||||
|
if branches:
|
||||||
|
issue_branches = [
|
||||||
|
b["name"] for b in branches
|
||||||
|
if str(issue_number) in b.get("name", "")
|
||||||
|
and b["name"] != "main"
|
||||||
|
]
|
||||||
|
if issue_branches:
|
||||||
|
warnings.append(f"Existing branches may target this issue: {issue_branches}")
|
||||||
|
|
||||||
|
# 5. Check for existing PRs
|
||||||
|
prs = gitea_get(f"/repos/{GITEA_OWNER}/{repo}/pulls?state=open&limit=50")
|
||||||
|
if prs:
|
||||||
|
issue_prs = [
|
||||||
|
f"PR #{p['number']}: {p['title']}"
|
||||||
|
for p in prs
|
||||||
|
if str(issue_number) in p.get("title", "")
|
||||||
|
or str(issue_number) in p.get("body", "")
|
||||||
|
]
|
||||||
|
if issue_prs:
|
||||||
|
failures.append(f"Open PR(s) already target this issue: {issue_prs}")
|
||||||
|
|
||||||
|
# 6. Check agent lanes
|
||||||
|
lanes = load_agent_lanes()
|
||||||
|
labels = [l.get("name", "") for l in (issue.get("labels") or [])]
|
||||||
|
lane_ok, lane_msg = check_agent_lane(agent, title, labels, lanes)
|
||||||
|
if not lane_ok:
|
||||||
|
warnings.append(lane_msg)
|
||||||
|
else:
|
||||||
|
messages.append(f" Lane: {lane_msg}")
|
||||||
|
|
||||||
|
# Report
|
||||||
|
if failures:
|
||||||
|
print("\n FAILURES:")
|
||||||
|
for f in failures:
|
||||||
|
print(f" ❌ {f}")
|
||||||
|
if warnings:
|
||||||
|
print("\n WARNINGS:")
|
||||||
|
for w in warnings:
|
||||||
|
print(f" ⚠️ {w}")
|
||||||
|
if not failures and not warnings:
|
||||||
|
print(" \u2705 All pre-task gates passed")
|
||||||
|
|
||||||
|
passed = len(failures) == 0
|
||||||
|
return passed, failures + warnings
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# POST-TASK GATE
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
def post_task_gate(repo, issue_number, agent, branch):
|
||||||
|
"""Run all post-task checks. Returns (pass, messages)."""
|
||||||
|
failures = []
|
||||||
|
warnings = []
|
||||||
|
|
||||||
|
print(f"\n=== POST-TASK GATE: {repo}#{issue_number} by {agent} ===")
|
||||||
|
print(f" Branch: {branch}")
|
||||||
|
|
||||||
|
# 1. Check branch exists
|
||||||
|
branch_info = gitea_get(
|
||||||
|
f"/repos/{GITEA_OWNER}/{repo}/branches/{urllib.parse.quote(branch, safe='')}"
|
||||||
|
)
|
||||||
|
if not branch_info:
|
||||||
|
failures.append(f"Branch '{branch}' does not exist")
|
||||||
|
return False, failures
|
||||||
|
|
||||||
|
# 2. Check branch naming convention
|
||||||
|
if "/" not in branch:
|
||||||
|
warnings.append(f"Branch name '{branch}' doesn't follow agent/description convention")
|
||||||
|
elif not branch.startswith(f"{agent}/"):
|
||||||
|
warnings.append(f"Branch '{branch}' doesn't start with agent name '{agent}/")
|
||||||
|
|
||||||
|
# 3. Check for commits ahead of main
|
||||||
|
compare = gitea_get(
|
||||||
|
f"/repos/{GITEA_OWNER}/{repo}/compare/main...{urllib.parse.quote(branch, safe='')}"
|
||||||
|
)
|
||||||
|
if compare:
|
||||||
|
commits = compare.get("commits", [])
|
||||||
|
if not commits:
|
||||||
|
failures.append("Branch has no commits ahead of main")
|
||||||
|
else:
|
||||||
|
print(f" Commits ahead: {len(commits)}")
|
||||||
|
files = compare.get("diff_files", []) or []
|
||||||
|
if not files:
|
||||||
|
# Try alternate key
|
||||||
|
num_files = compare.get("total_commits", 0)
|
||||||
|
print(f" Files changed: (check PR diff)")
|
||||||
|
else:
|
||||||
|
print(f" Files changed: {len(files)}")
|
||||||
|
|
||||||
|
# 4. Check for duplicate PRs
|
||||||
|
prs = gitea_get(f"/repos/{GITEA_OWNER}/{repo}/pulls?state=open&limit=50")
|
||||||
|
if prs:
|
||||||
|
dupe_prs = [
|
||||||
|
f"PR #{p['number']}"
|
||||||
|
for p in prs
|
||||||
|
if str(issue_number) in p.get("title", "")
|
||||||
|
or str(issue_number) in p.get("body", "")
|
||||||
|
]
|
||||||
|
if len(dupe_prs) > 1:
|
||||||
|
warnings.append(f"Multiple open PRs may target issue #{issue_number}: {dupe_prs}")
|
||||||
|
|
||||||
|
# 5. Run syntax guard on changed files (if available)
|
||||||
|
syntax_guard = os.path.join(
|
||||||
|
os.path.dirname(os.path.dirname(os.path.abspath(__file__))),
|
||||||
|
"hermes-sovereign", "scripts", "syntax_guard.py"
|
||||||
|
)
|
||||||
|
if os.path.exists(syntax_guard):
|
||||||
|
try:
|
||||||
|
result = subprocess.run(
|
||||||
|
[sys.executable, syntax_guard],
|
||||||
|
capture_output=True, text=True, timeout=30
|
||||||
|
)
|
||||||
|
if result.returncode != 0:
|
||||||
|
failures.append(f"Syntax guard failed: {result.stdout[:200]}")
|
||||||
|
else:
|
||||||
|
print(" Syntax guard: passed")
|
||||||
|
except Exception as e:
|
||||||
|
warnings.append(f"Could not run syntax guard: {e}")
|
||||||
|
else:
|
||||||
|
warnings.append("syntax_guard.py not found — skipping syntax check")
|
||||||
|
|
||||||
|
# Report
|
||||||
|
if failures:
|
||||||
|
print("\n FAILURES:")
|
||||||
|
for f in failures:
|
||||||
|
print(f" ❌ {f}")
|
||||||
|
if warnings:
|
||||||
|
print("\n WARNINGS:")
|
||||||
|
for w in warnings:
|
||||||
|
print(f" ⚠️ {w}")
|
||||||
|
if not failures and not warnings:
|
||||||
|
print(" \u2705 All post-task gates passed")
|
||||||
|
|
||||||
|
passed = len(failures) == 0
|
||||||
|
return passed, failures + warnings
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# MAIN
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Task Gate — pre/post-task quality gates")
|
||||||
|
subparsers = parser.add_subparsers(dest="command")
|
||||||
|
|
||||||
|
# Pre-task
|
||||||
|
pre = subparsers.add_parser("pre", help="Run pre-task gates")
|
||||||
|
pre.add_argument("--repo", required=True)
|
||||||
|
pre.add_argument("--issue", type=int, required=True)
|
||||||
|
pre.add_argument("--agent", required=True)
|
||||||
|
|
||||||
|
# Post-task
|
||||||
|
post = subparsers.add_parser("post", help="Run post-task gates")
|
||||||
|
post.add_argument("--repo", required=True)
|
||||||
|
post.add_argument("--issue", type=int, required=True)
|
||||||
|
post.add_argument("--agent", required=True)
|
||||||
|
post.add_argument("--branch", required=True)
|
||||||
|
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
if not args.command:
|
||||||
|
parser.print_help()
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
if args.command == "pre":
|
||||||
|
passed, msgs = pre_task_gate(args.repo, args.issue, args.agent)
|
||||||
|
elif args.command == "post":
|
||||||
|
passed, msgs = post_task_gate(args.repo, args.issue, args.agent, args.branch)
|
||||||
|
else:
|
||||||
|
parser.print_help()
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
sys.exit(0 if passed else 1)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user