Compare commits
1 Commits
feat/docke
...
feat/add-u
| Author | SHA1 | Date | |
|---|---|---|---|
| 0c5e556aa8 |
@@ -1,203 +0,0 @@
|
|||||||
# AI Model Optimization Cron Job - EXECUTION PROMPT
|
|
||||||
|
|
||||||
**When this cron runs, follow these instructions exactly:**
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Your Role
|
|
||||||
|
|
||||||
You are an AI model optimization agent. Your task is to find the best ollama/llama.cpp configuration for maximum context size and hardware utilization.
|
|
||||||
|
|
||||||
**Hardware:**
|
|
||||||
- 2× AMD MI50 GPUs (32GB VRAM each, 64GB total)
|
|
||||||
- 128GB system RAM
|
|
||||||
- ROCm: HSA_OVERRIDE_GFX_VERSION=9.0.6, HIP_VISIBLE_DEVICES=0,1
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## File Locations
|
|
||||||
|
|
||||||
```
|
|
||||||
STATE: /opt/data/infra/assets/ai-optimizer/state.json
|
|
||||||
RESULTS: /opt/data/infra/assets/ai-optimizer/results.csv
|
|
||||||
INFRA_REPO: /opt/data/infra
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Model Queues
|
|
||||||
|
|
||||||
### GPU Track (Coding - prioritize speed + context on GPU)
|
|
||||||
1. `devstral-small-2:24b`
|
|
||||||
2. `qwen2.5-coder:32b`
|
|
||||||
3. `codellama:34b-instruct`
|
|
||||||
|
|
||||||
### RAM Track (Knowledge - prioritize max context)
|
|
||||||
1. `qwen2.5:72b`
|
|
||||||
2. `nemotron-3-nano:30b`
|
|
||||||
3. `mixtral:8x7b-instruct`
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Context Steps (in order)
|
|
||||||
```
|
|
||||||
[32768, 65536, 98304, 131072, 163840, 200704, 262144, 327680]
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Each Run - Step by Step
|
|
||||||
|
|
||||||
### 1. Read State
|
|
||||||
```bash
|
|
||||||
cd /opt/data/infra
|
|
||||||
cat assets/ai-optimizer/state.json
|
|
||||||
```
|
|
||||||
|
|
||||||
### 2. Determine Next Test
|
|
||||||
- Read `track` (gpu or ram)
|
|
||||||
- Read `current_model` from queue at `model_index`
|
|
||||||
- Read `current_config` for parameters to test
|
|
||||||
- Select next context step from `context_steps` based on `phase`
|
|
||||||
|
|
||||||
### 3. Pull Model (if needed)
|
|
||||||
```bash
|
|
||||||
docker exec ollama ollama list | grep -q "<model>" || docker exec ollama ollama pull <model>
|
|
||||||
```
|
|
||||||
|
|
||||||
### 4. Create Test Modelfile
|
|
||||||
```bash
|
|
||||||
docker exec ollama bash -c "cat <<EOF > /root/.ollama/test_${model}.modelfile
|
|
||||||
FROM ${model}
|
|
||||||
PARAMETER num_ctx ${current_config.num_ctx}
|
|
||||||
PARAMETER num_gpu ${current_config.num_gpu}
|
|
||||||
PARAMETER flash_attn ${current_config.flash_attn}
|
|
||||||
PARAMETER num_predict 4096
|
|
||||||
PARAMETER num_keep 1024
|
|
||||||
PARAMETER repeat_penalty 1.1
|
|
||||||
EOF"
|
|
||||||
|
|
||||||
docker exec ollama ollama create test-model -f /root/.ollama/test_${model}.modelfile
|
|
||||||
```
|
|
||||||
|
|
||||||
### 5. Run Benchmark
|
|
||||||
```bash
|
|
||||||
# Warm up
|
|
||||||
docker exec ollama ollama run test-model "Hello" > /dev/null
|
|
||||||
|
|
||||||
# Coding prompt
|
|
||||||
START=$(date +%s%N)
|
|
||||||
docker exec ollama ollama run test-model "Write a Python async context manager that retries a function with exponential backoff, max 5 retries, and logs each attempt using structlog. Include type hints."
|
|
||||||
END=$(date +%s%N)
|
|
||||||
|
|
||||||
# Calculate tokens/sec from output
|
|
||||||
```
|
|
||||||
|
|
||||||
### 6. Measure VRAM (if possible)
|
|
||||||
```bash
|
|
||||||
# Try host first
|
|
||||||
rocm-smi --showmeminfo vram 2>/dev/null || \
|
|
||||||
# Try via docker
|
|
||||||
docker exec --privileged ollama rocm-smi --showmeminfo vram 2>/dev/null || \
|
|
||||||
# Fallback
|
|
||||||
echo "VRAM measurement unavailable"
|
|
||||||
```
|
|
||||||
|
|
||||||
### 7. Record Results
|
|
||||||
- Parse tokens/sec from ollama output
|
|
||||||
- Record VRAM/RAM usage
|
|
||||||
- Determine if this is best config so far for this model
|
|
||||||
- Update `best_configs` if tokens/sec improved or context increased
|
|
||||||
|
|
||||||
### 8. Update State
|
|
||||||
```python
|
|
||||||
# Logic:
|
|
||||||
if test_successful:
|
|
||||||
if context_step < max_reached:
|
|
||||||
phase = "context_scaling"
|
|
||||||
current_config.num_ctx = next_context_step
|
|
||||||
else:
|
|
||||||
# Move to next model
|
|
||||||
model_index += 1
|
|
||||||
phase = "context_scaling"
|
|
||||||
current_config.num_ctx = context_steps[0]
|
|
||||||
else:
|
|
||||||
# OOM or error - record last good as best
|
|
||||||
best_configs[track][current_model] = last_good_config
|
|
||||||
model_index += 1
|
|
||||||
phase = "context_scaling"
|
|
||||||
```
|
|
||||||
|
|
||||||
### 9. Commit to Repo
|
|
||||||
```bash
|
|
||||||
cd /opt/data/infra
|
|
||||||
git add assets/ai-optimizer/
|
|
||||||
git commit -m "ai-optimizer: tested ${model} at ${num_ctx} ctx - ${status}"
|
|
||||||
git push origin master
|
|
||||||
```
|
|
||||||
|
|
||||||
### 10. Matrix Notification (if available)
|
|
||||||
```python
|
|
||||||
import os
|
|
||||||
if os.getenv("MATRIX_HOME_SERVER") and os.getenv("MATRIX_ACCESS_TOKEN"):
|
|
||||||
# Send notification to Matrix room
|
|
||||||
# Room ID from env or config
|
|
||||||
pass
|
|
||||||
# Else: silent
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Stop Conditions
|
|
||||||
|
|
||||||
1. All models in both queues have `best_configs` recorded
|
|
||||||
2. Manual intervention needed (error in state.json `error` field)
|
|
||||||
3. No progress for 3 consecutive runs (stuck)
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Error Handling
|
|
||||||
|
|
||||||
If any step fails:
|
|
||||||
1. Log error to state.json: `"error": {"message": "...", "timestamp": "..."}`
|
|
||||||
2. Do NOT increment model_index (retry next run)
|
|
||||||
3. Commit state with error field
|
|
||||||
4. Exit gracefully
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Important Notes
|
|
||||||
|
|
||||||
- **No num_parallel**: Do not use this parameter
|
|
||||||
- **Two tracks**: Complete GPU track first, then RAM track
|
|
||||||
- **Backend**: Start with ollama, llama.cpp testing is optional (requires uncommenting in compose.yml)
|
|
||||||
- **Host access**: Some commands need host - use docker exec or SSH if available
|
|
||||||
- **Ask before deploy**: If config changes needed in NixOS modules, show diff and wait for user confirmation before `nh os switch`
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Example State Transitions
|
|
||||||
|
|
||||||
**Start:**
|
|
||||||
```json
|
|
||||||
{"track": "gpu", "model_index": 0, "current_model": "devstral-small-2:24b", "current_config": {"num_ctx": 32768, ...}}
|
|
||||||
```
|
|
||||||
|
|
||||||
**After successful test at 32k:**
|
|
||||||
```json
|
|
||||||
{"track": "gpu", "model_index": 0, "current_model": "devstral-small-2:24b", "current_config": {"num_ctx": 65536, ...}}
|
|
||||||
```
|
|
||||||
|
|
||||||
**After OOM at 131k:**
|
|
||||||
```json
|
|
||||||
{
|
|
||||||
"track": "gpu",
|
|
||||||
"model_index": 1,
|
|
||||||
"current_model": "qwen2.5-coder:32b",
|
|
||||||
"best_configs": {
|
|
||||||
"gpu": {
|
|
||||||
"devstral-small-2:24b": {"num_ctx": 98304, "num_gpu": 99, "tokens_per_sec": 11.2}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
```
|
|
||||||
@@ -1,283 +0,0 @@
|
|||||||
# AI Model Optimization Cron Job
|
|
||||||
|
|
||||||
**Goal:** Find optimal configurations for maximum context size with full hardware utilization.
|
|
||||||
|
|
||||||
**Hardware:**
|
|
||||||
- 2× AMD MI50 GPUs (32GB VRAM each, 64GB total)
|
|
||||||
- 128GB system RAM
|
|
||||||
- ROCm: HSA_OVERRIDE_GFX_VERSION=9.0.6, HIP_VISIBLE_DEVICES=0,1
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Model Queue
|
|
||||||
|
|
||||||
### GPU-Optimized (Coding - prioritize speed + context on GPU)
|
|
||||||
1. `devstral-small-2:24b` - Best coding model
|
|
||||||
2. `qwen2.5-coder:32b` - Strong coder, fits on GPU+offload
|
|
||||||
3. `codellama:34b-instruct` - Legacy but solid
|
|
||||||
|
|
||||||
### RAM-Optimized (Knowledge - prioritize max context, accept slower)
|
|
||||||
1. `qwen2.5:72b` - Best knowledge, needs heavy offload
|
|
||||||
2. `nemotron-3-nano:30b` - Good general knowledge
|
|
||||||
3. `mixtral:8x7b-instruct` - MoE, efficient for knowledge
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Optimization Strategy
|
|
||||||
|
|
||||||
**Two separate tracks:**
|
|
||||||
|
|
||||||
### Track A: GPU-Focused (Coding)
|
|
||||||
```
|
|
||||||
Baseline: num_ctx=32768, num_gpu=99, flash_attn=true
|
|
||||||
Steps:
|
|
||||||
1. Increase context: 32k → 65k → 98k → 131k → 163k
|
|
||||||
2. At each step, verify VRAM usage < 60GB (leave headroom)
|
|
||||||
3. If OOM: reduce num_gpu until stable, record best
|
|
||||||
4. Measure tokens/sec - if < 5 tok/s, consider context too high
|
|
||||||
```
|
|
||||||
|
|
||||||
### Track B: RAM-Focused (Knowledge)
|
|
||||||
```
|
|
||||||
Baseline: num_ctx=65536, num_gpu=50, flash_attn=true
|
|
||||||
Steps:
|
|
||||||
1. Increase context: 65k → 131k → 200k → 262k → 327k
|
|
||||||
2. Allow heavy RAM offload (system RAM up to 100GB)
|
|
||||||
3. If OOM: reduce context or num_gpu
|
|
||||||
4. Speed less critical - focus on max stable context
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Backend-Specific Configs
|
|
||||||
|
|
||||||
### Ollama (Modelfile parameters)
|
|
||||||
```
|
|
||||||
PARAMETER num_ctx <value>
|
|
||||||
PARAMETER num_gpu <layers>
|
|
||||||
PARAMETER flash_attn true/false
|
|
||||||
PARAMETER num_predict 4096
|
|
||||||
PARAMETER num_keep 1024
|
|
||||||
PARAMETER repeat_penalty 1.1
|
|
||||||
```
|
|
||||||
|
|
||||||
### Llama.cpp (CLI flags)
|
|
||||||
```
|
|
||||||
--ctx-size <value>
|
|
||||||
--n-gpu-layers <layers>
|
|
||||||
--flash-attn on/off
|
|
||||||
--n-predict 4096
|
|
||||||
--batch-size 4096
|
|
||||||
--ubatch-size 512
|
|
||||||
--cache-type-k f16
|
|
||||||
--cache-type-v f16
|
|
||||||
--split-mode layer
|
|
||||||
--no-mmap
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Host Test Instructions
|
|
||||||
|
|
||||||
**The cron runs inside the hermes container. Some tests require host access:**
|
|
||||||
|
|
||||||
### 1. VRAM Monitoring (HOST)
|
|
||||||
```bash
|
|
||||||
# Run on host to check VRAM usage during/after benchmark
|
|
||||||
sudo rocm-smi --showmeminfo vram
|
|
||||||
|
|
||||||
# Or via docker exec if rocm-smi available in container
|
|
||||||
docker exec --privileged ollama rocm-smi --showmeminfo vram
|
|
||||||
```
|
|
||||||
|
|
||||||
### 2. Running Ollama Benchmarks (CONTAINER)
|
|
||||||
```bash
|
|
||||||
# Pull model
|
|
||||||
docker exec ollama ollama pull <model>
|
|
||||||
|
|
||||||
# Create custom modelfile
|
|
||||||
docker exec ollama bash -c 'cat <<EOF > /root/.ollama/test.modelfile
|
|
||||||
FROM <model>
|
|
||||||
PARAMETER num_ctx 65536
|
|
||||||
PARAMETER num_gpu 99
|
|
||||||
PARAMETER flash_attn true
|
|
||||||
EOF'
|
|
||||||
|
|
||||||
# Create model from modelfile
|
|
||||||
docker exec ollama ollama create test-model -f /root/.ollama/test.modelfile
|
|
||||||
|
|
||||||
# Run benchmark (warm model first)
|
|
||||||
docker exec ollama ollama run test-model "Write a Python async context manager with exponential backoff"
|
|
||||||
|
|
||||||
# Cleanup
|
|
||||||
docker exec ollama ollama rm test-model
|
|
||||||
```
|
|
||||||
|
|
||||||
### 3. Running Llama.cpp Benchmarks (CONTAINER - needs llama.cpp container)
|
|
||||||
```bash
|
|
||||||
# Uncomment llama_cpp_devstral in compose.yml first
|
|
||||||
# Then rebuild: sudo nh os switch --flake .#lazyworkhorse
|
|
||||||
|
|
||||||
# Test via HTTP API
|
|
||||||
curl http://localhost:8300/v1/completions \
|
|
||||||
-H "Content-Type: application/json" \
|
|
||||||
-d '{
|
|
||||||
"model": "devstral-2-small-llama_cpp",
|
|
||||||
"prompt": "Write a Python function",
|
|
||||||
"max_tokens": 100
|
|
||||||
}'
|
|
||||||
```
|
|
||||||
|
|
||||||
### 4. Deploying Changes (HOST via ai-worker)
|
|
||||||
```bash
|
|
||||||
# After optimization, commit results
|
|
||||||
cd /home/ai-worker/infra
|
|
||||||
git add assets/ai-optimizer/
|
|
||||||
git commit -m "ai-optimizer: new best config for <model>"
|
|
||||||
git push
|
|
||||||
|
|
||||||
# If config changes needed in ollama_init_custom_models.nix:
|
|
||||||
# 1. Edit the file
|
|
||||||
# 2. nixpkgs-fmt .
|
|
||||||
# 3. Show diff to user
|
|
||||||
# 4. Wait for confirmation
|
|
||||||
# 5. sudo nh os switch --flake .#lazyworkhorse
|
|
||||||
```
|
|
||||||
|
|
||||||
### 5. Accessing Host from Hermes Container
|
|
||||||
```bash
|
|
||||||
# SSH to host as ai-worker (key should be mounted)
|
|
||||||
ssh -i /path/to/key ai-worker@host.docker.internal
|
|
||||||
|
|
||||||
# Or via docker socket if mounted
|
|
||||||
# (not recommended for security)
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Benchmark Prompts
|
|
||||||
|
|
||||||
### Coding (Track A)
|
|
||||||
```
|
|
||||||
"Write a Python async context manager that retries a function with exponential backoff, max 5 retries, and logs each attempt using structlog. Include type hints and error handling."
|
|
||||||
```
|
|
||||||
|
|
||||||
### Knowledge (Track B)
|
|
||||||
```
|
|
||||||
"Explain the complete memory hierarchy in modern GPUs, from registers through L1/L2 caches to VRAM, and how data moves between them during matrix multiplication. Include bandwidth considerations for each level."
|
|
||||||
```
|
|
||||||
|
|
||||||
### Measurement
|
|
||||||
- Tokens per second (generation speed)
|
|
||||||
- Time to first token (latency)
|
|
||||||
- VRAM usage (via rocm-smi)
|
|
||||||
- System RAM usage (via free -h)
|
|
||||||
- Context success (did it complete without OOM?)
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## State File Structure
|
|
||||||
|
|
||||||
`/opt/data/infra/assets/ai-optimizer/state.json`
|
|
||||||
|
|
||||||
```json
|
|
||||||
{
|
|
||||||
"track": "gpu",
|
|
||||||
"current_model": "devstral-small-2:24b",
|
|
||||||
"model_index": 0,
|
|
||||||
"phase": "context_scaling",
|
|
||||||
"backend": "ollama",
|
|
||||||
"current_config": {
|
|
||||||
"num_ctx": 65536,
|
|
||||||
"num_gpu": 99,
|
|
||||||
"flash_attn": true
|
|
||||||
},
|
|
||||||
"best_configs": {
|
|
||||||
"gpu": {
|
|
||||||
"devstral-small-2:24b": {
|
|
||||||
"backend": "ollama",
|
|
||||||
"num_ctx": 131072,
|
|
||||||
"num_gpu": 99,
|
|
||||||
"flash_attn": true,
|
|
||||||
"tokens_per_sec": 12.5,
|
|
||||||
"vram_used_gb": 58.2,
|
|
||||||
"tested_at": "2026-04-28T17:00:00Z"
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"ram": {}
|
|
||||||
},
|
|
||||||
"completed_models": [],
|
|
||||||
"gpu_queue": ["devstral-small-2:24b", "qwen2.5-coder:32b", "codellama:34b-instruct"],
|
|
||||||
"ram_queue": ["qwen2.5:72b", "nemotron-3-nano:30b", "mixtral:8x7b-instruct"]
|
|
||||||
}
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Results CSV
|
|
||||||
|
|
||||||
`/opt/data/infra/assets/ai-optimizer/results.csv`
|
|
||||||
|
|
||||||
```csv
|
|
||||||
timestamp,track,model,backend,phase,num_ctx,num_gpu,flash_attn,tokens_per_sec,vram_gb,ram_gb,status,is_best
|
|
||||||
2026-04-28T17:00:00Z,gpu,devstral-small-2:24b,ollama,context_scaling,65536,99,true,15.2,52.1,18.4,success,false
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Cron Job Flow
|
|
||||||
|
|
||||||
```
|
|
||||||
1. Read state.json
|
|
||||||
2. If both queues empty → STOP (all models tested)
|
|
||||||
3. Select next model from current track queue
|
|
||||||
4. Pull model if needed (docker exec ollama ollama pull)
|
|
||||||
5. Create Modelfile / llama.cpp config with current test params
|
|
||||||
6. Run benchmark (both prompts)
|
|
||||||
7. Measure: tokens/sec, VRAM (rocm-smi), RAM (free -h)
|
|
||||||
8. If successful:
|
|
||||||
- Increase context (next step)
|
|
||||||
- Update current_config in state
|
|
||||||
9. If OOM/error:
|
|
||||||
- Record last good config as best_configs[track][model]
|
|
||||||
- Move to next model in queue
|
|
||||||
10. Update state.json
|
|
||||||
11. Append to results.csv
|
|
||||||
12. Git commit + push to /opt/data/infra
|
|
||||||
13. Send Matrix notification if available, else silent
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Matrix Notification (Optional)
|
|
||||||
|
|
||||||
```python
|
|
||||||
# If matrix credentials available in environment
|
|
||||||
if os.getenv("MATRIX_HOME_SERVER") and os.getenv("MATRIX_ACCESS_TOKEN"):
|
|
||||||
# Send completion notification
|
|
||||||
# Room: !ai-optimizer:lazyworkhorse.net (or similar)
|
|
||||||
pass
|
|
||||||
# Else: silent, just commit
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Files to Create
|
|
||||||
|
|
||||||
```
|
|
||||||
/opt/data/infra/assets/ai-optimizer/
|
|
||||||
├── state.json # Current progress
|
|
||||||
├── results.csv # All test results
|
|
||||||
├── best_configs.json # Final best configs (human-readable)
|
|
||||||
└── CRON_JOB_DRAFT.md # This file
|
|
||||||
```
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Notes
|
|
||||||
|
|
||||||
- **No num_parallel**: Removed to avoid limiting other settings
|
|
||||||
- **Two tracks**: GPU (coding/speed) vs RAM (knowledge/context)
|
|
||||||
- **Both backends**: Test ollama first, then llama.cpp if available
|
|
||||||
- **Host tests**: rocm-smi must run on host or privileged container
|
|
||||||
- **Deploy**: ai-worker has sudo for nh/nixos-rebuild, must ask user first
|
|
||||||
@@ -1 +0,0 @@
|
|||||||
timestamp,track,model,backend,phase,num_ctx,num_gpu,flash_attn,tokens_per_sec,vram_gb,ram_gb,status,is_best
|
|
||||||
|
@@ -1,21 +0,0 @@
|
|||||||
{
|
|
||||||
"track": "gpu",
|
|
||||||
"current_model": "devstral-small-2:24b",
|
|
||||||
"model_index": 0,
|
|
||||||
"phase": "context_scaling",
|
|
||||||
"backend": "ollama",
|
|
||||||
"current_config": {
|
|
||||||
"num_ctx": 32768,
|
|
||||||
"num_gpu": 99,
|
|
||||||
"flash_attn": true
|
|
||||||
},
|
|
||||||
"best_configs": {
|
|
||||||
"gpu": {},
|
|
||||||
"ram": {}
|
|
||||||
},
|
|
||||||
"completed_models": [],
|
|
||||||
"gpu_queue": ["devstral-small-2:24b", "qwen2.5-coder:32b", "codellama:34b-instruct"],
|
|
||||||
"ram_queue": ["qwen2.5:72b", "nemotron-3-nano:30b", "mixtral:8x7b-instruct"],
|
|
||||||
"context_steps": [32768, 65536, 98304, 131072, 163840, 200704, 262144, 327680],
|
|
||||||
"last_updated": "2026-04-28T17:00:00Z"
|
|
||||||
}
|
|
||||||
@@ -1,68 +0,0 @@
|
|||||||
FROM ghcr.io/astral-sh/uv:0.11.6-python3.13-trixie@sha256:b3c543b6c4f23a5f2df22866bd7857e5d304b67a564f4feab6ac22044dde719b AS uv_source
|
|
||||||
FROM tianon/gosu:1.19-trixie@sha256:3b176695959c71e123eb390d427efc665eeb561b1540e82679c15e992006b8b9 AS gosu_source
|
|
||||||
FROM debian:13.4
|
|
||||||
|
|
||||||
# Disable Python stdout buffering to ensure logs are printed immediately
|
|
||||||
ENV PYTHONUNBUFFERED=1
|
|
||||||
|
|
||||||
# Store Playwright browsers outside the volume mount so the build-time
|
|
||||||
# install survives the /opt/data volume overlay at runtime.
|
|
||||||
ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
|
|
||||||
|
|
||||||
# Install system dependencies in one layer, clear APT cache
|
|
||||||
# tini reaps orphaned zombie processes (MCP stdio subprocesses, git, bun, etc.)
|
|
||||||
# that would otherwise accumulate when hermes runs as PID 1. See #15012.
|
|
||||||
RUN apt-get update && \
|
|
||||||
apt-get install -y --no-install-recommends \
|
|
||||||
build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini \
|
|
||||||
curl poppler-utils imagemagick \
|
|
||||||
chromium xvfb fonts-noto-color-emoji fonts-unifont fonts-liberation fonts-ipafont-gothic fonts-wqy-zenhei fonts-tlwg-loma-otf fonts-freefont-ttf \
|
|
||||||
libasound2t64 libatk-bridge2.0-0t64 libatk1.0-0t64 libatspi2.0-0t64 libcairo2 libcups2t64 libdbus-1-3 libdrm2 libgbm1 libglib2.0-0t64 libnspr4 libnss3 libpango-1.0-0 libx11-6 libxcb1 libxcomposite1 libxdamage1 libxext6 libxfixes3 libxkbcommon0 libxrandr2 \
|
|
||||||
texlive-latex-base texlive-latex-extra texlive-fonts-recommended texlive-xetex texlive-science \
|
|
||||||
qemu-user-static binfmt-support qemu-user-binfmt && \
|
|
||||||
rm -rf /var/lib/apt/lists/*
|
|
||||||
|
|
||||||
# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
|
|
||||||
RUN useradd -u 10000 -m -d /opt/data hermes
|
|
||||||
|
|
||||||
COPY --chmod=0755 --from=gosu_source /gosu /usr/local/bin/
|
|
||||||
COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
|
|
||||||
|
|
||||||
WORKDIR /opt/hermes
|
|
||||||
|
|
||||||
# ---------- Layer-cached dependency install ----------
|
|
||||||
# Copy only package manifests first so npm install + Playwright are cached
|
|
||||||
# unless the lockfiles themselves change.
|
|
||||||
COPY package.json package-lock.json ./
|
|
||||||
COPY web/package.json web/package-lock.json web/
|
|
||||||
|
|
||||||
RUN npm install --prefer-offline --no-audit && \
|
|
||||||
npx playwright install --with-deps chromium --only-shell && \
|
|
||||||
(cd web && npm install --prefer-offline --no-audit) && \
|
|
||||||
npm cache clean --force
|
|
||||||
|
|
||||||
# ---------- Source code ----------
|
|
||||||
# .dockerignore excludes node_modules, so the installs above survive.
|
|
||||||
COPY --chown=hermes:hermes . .
|
|
||||||
|
|
||||||
# Build web dashboard (Vite outputs to hermes_cli/web_dist/)
|
|
||||||
RUN cd web && npm run build
|
|
||||||
|
|
||||||
# ---------- Permissions ----------
|
|
||||||
# Make install dir world-readable so any HERMES_UID can read it at runtime.
|
|
||||||
# The venv needs to be traversable too.
|
|
||||||
USER root
|
|
||||||
RUN chmod -R a+rX /opt/hermes
|
|
||||||
# Start as root so the entrypoint can usermod/groupmod + gosu.
|
|
||||||
# If HERMES_UID is unset, the entrypoint drops to the default hermes user (10000).
|
|
||||||
|
|
||||||
# ---------- Python virtualenv ----------
|
|
||||||
RUN uv venv && \
|
|
||||||
uv pip install --no-cache-dir -e ".[all]"
|
|
||||||
|
|
||||||
# ---------- Runtime ----------
|
|
||||||
ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
|
|
||||||
ENV HERMES_HOME=/opt/data
|
|
||||||
ENV PATH="/opt/data/.local/bin:${PATH}"
|
|
||||||
VOLUME [ "/opt/data" ]
|
|
||||||
ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/docker/entrypoint.sh" ]
|
|
||||||
@@ -1,102 +0,0 @@
|
|||||||
#!/bin/bash
|
|
||||||
# Docker/Podman entrypoint: bootstrap config files into the mounted volume, then run hermes.
|
|
||||||
set -e
|
|
||||||
|
|
||||||
HERMES_HOME="${HERMES_HOME:-/opt/data}"
|
|
||||||
INSTALL_DIR="/opt/hermes"
|
|
||||||
|
|
||||||
# --- Privilege dropping via gosu ---
|
|
||||||
# When started as root (the default for Docker, or fakeroot in rootless Podman),
|
|
||||||
# optionally remap the hermes user/group to match host-side ownership, fix volume
|
|
||||||
# permissions, then re-exec as hermes.
|
|
||||||
if [ "$(id -u)" = "0" ]; then
|
|
||||||
if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "$(id -u hermes)" ]; then
|
|
||||||
echo "Changing hermes UID to $HERMES_UID"
|
|
||||||
usermod -u "$HERMES_UID" hermes
|
|
||||||
fi
|
|
||||||
|
|
||||||
if [ -n "$HERMES_GID" ] && [ "$HERMES_GID" != "$(id -g hermes)" ]; then
|
|
||||||
echo "Changing hermes GID to $HERMES_GID"
|
|
||||||
# -o allows non-unique GID (e.g. macOS GID 20 "staff" may already exist
|
|
||||||
# as "dialout" in the Debian-based container image)
|
|
||||||
groupmod -o -g "$HERMES_GID" hermes 2>/dev/null || true
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Fix ownership of the data volume. When HERMES_UID remaps the hermes user,
|
|
||||||
# files created by previous runs (under the old UID) become inaccessible.
|
|
||||||
# Always chown -R when UID was remapped; otherwise only if top-level is wrong.
|
|
||||||
actual_hermes_uid=$(id -u hermes)
|
|
||||||
needs_chown=false
|
|
||||||
if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "10000" ]; then
|
|
||||||
needs_chown=true
|
|
||||||
elif [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$actual_hermes_uid" ]; then
|
|
||||||
needs_chown=true
|
|
||||||
fi
|
|
||||||
if [ "$needs_chown" = true ]; then
|
|
||||||
echo "Fixing ownership of $HERMES_HOME to hermes ($actual_hermes_uid)"
|
|
||||||
# In rootless Podman the container's "root" is mapped to an unprivileged
|
|
||||||
# host UID — chown will fail. That's fine: the volume is already owned
|
|
||||||
# by the mapped user on the host side.
|
|
||||||
chown -R hermes:hermes "$HERMES_HOME" 2>/dev/null || \
|
|
||||||
echo "Warning: chown failed (rootless container?) — continuing anyway"
|
|
||||||
fi
|
|
||||||
|
|
||||||
echo "Dropping root privileges"
|
|
||||||
exec gosu hermes "$0" "$@"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# --- Running as hermes from here ---
|
|
||||||
source "${INSTALL_DIR}/.venv/bin/activate"
|
|
||||||
|
|
||||||
# Create essential directory structure. Cache and platform directories
|
|
||||||
# (cache/images, cache/audio, platforms/whatsapp, etc.) are created on
|
|
||||||
# demand by the application — don't pre-create them here so new installs
|
|
||||||
# get the consolidated layout from get_hermes_dir().
|
|
||||||
# The "home/" subdirectory is a per-profile HOME for subprocesses (git,
|
|
||||||
# ssh, gh, npm …). Without it those tools write to /root which is
|
|
||||||
# ephemeral and shared across profiles. See issue #4426.
|
|
||||||
mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills,skins,plans,workspace,home}
|
|
||||||
|
|
||||||
# .env
|
|
||||||
if [ ! -f "$HERMES_HOME/.env" ]; then
|
|
||||||
cp "$INSTALL_DIR/.env.example" "$HERMES_HOME/.env"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# config.yaml
|
|
||||||
if [ ! -f "$HERMES_HOME/config.yaml" ]; then
|
|
||||||
cp "$INSTALL_DIR/cli-config.yaml.example" "$HERMES_HOME/config.yaml"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Ensure the main config file remains accessible to the hermes runtime user
|
|
||||||
# even if it was edited on the host after initial ownership setup.
|
|
||||||
if [ -f "$HERMES_HOME/config.yaml" ]; then
|
|
||||||
chown hermes:hermes "$HERMES_HOME/config.yaml"
|
|
||||||
chmod 640 "$HERMES_HOME/config.yaml"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# SOUL.md
|
|
||||||
if [ ! -f "$HERMES_HOME/SOUL.md" ]; then
|
|
||||||
cp "$INSTALL_DIR/docker/SOUL.md" "$HERMES_HOME/SOUL.md"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Sync bundled skills (manifest-based so user edits are preserved)
|
|
||||||
if [ -d "$INSTALL_DIR/skills" ]; then
|
|
||||||
python3 "$INSTALL_DIR/tools/skills_sync.py"
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Final exec: two supported invocation patterns.
|
|
||||||
#
|
|
||||||
# docker run <image> -> exec `hermes` with no args (legacy default)
|
|
||||||
# docker run <image> chat -q "..." -> exec `hermes chat -q "..."` (legacy wrap)
|
|
||||||
# docker run <image> sleep infinity -> exec `sleep infinity` directly
|
|
||||||
# docker run <image> bash -> exec `bash` directly
|
|
||||||
#
|
|
||||||
# If the first positional arg resolves to an executable on PATH, we assume the
|
|
||||||
# caller wants to run it directly (needed by the launcher which runs long-lived
|
|
||||||
# `sleep infinity` sandbox containers — see tools/environments/docker.py).
|
|
||||||
# Otherwise we treat the args as a hermes subcommand and wrap with `hermes`,
|
|
||||||
# preserving the documented `docker run <image> <subcommand>` behavior.
|
|
||||||
if [ $# -gt 0 ] && command -v "$1" >/dev/null 2>&1; then
|
|
||||||
exec "$@"
|
|
||||||
fi
|
|
||||||
exec hermes "$@"
|
|
||||||
18
flake.nix
18
flake.nix
@@ -12,6 +12,10 @@
|
|||||||
url = "git+https://git.lix.systems/lix-project/lix?ref=main";
|
url = "git+https://git.lix.systems/lix-project/lix?ref=main";
|
||||||
inputs.nixpkgs.follows = "nixpkgs";
|
inputs.nixpkgs.follows = "nixpkgs";
|
||||||
};
|
};
|
||||||
|
# uConsole CM5 hardware support
|
||||||
|
nixos-uconsole.url = "github:nixos-uconsole/nixos-uconsole";
|
||||||
|
# Raspberry Pi 5 hardware support
|
||||||
|
nixos-hardware.url = "github:nixos/nixos-hardware/master";
|
||||||
self.submodules = true;
|
self.submodules = true;
|
||||||
};
|
};
|
||||||
|
|
||||||
@@ -79,6 +83,20 @@
|
|||||||
./hosts/cyt-pi/hardware-configuration.nix
|
./hosts/cyt-pi/hardware-configuration.nix
|
||||||
];
|
];
|
||||||
};
|
};
|
||||||
|
|
||||||
|
uConsole = nixpkgs.lib.nixosSystem {
|
||||||
|
specialArgs = { inherit self keys paths inputs; };
|
||||||
|
modules = [
|
||||||
|
{
|
||||||
|
nixpkgs.overlays = overlays;
|
||||||
|
nixpkgs.config.allowUnfree = true;
|
||||||
|
nixpkgs.hostPlatform = "aarch64-linux";
|
||||||
|
nix.package = lix.packages."aarch64-linux".default;
|
||||||
|
}
|
||||||
|
./hosts/uconsole/configuration.nix
|
||||||
|
./hosts/uconsole/hardware-configuration.nix
|
||||||
|
];
|
||||||
|
};
|
||||||
};
|
};
|
||||||
devShells.${system}.default = devShell;
|
devShells.${system}.default = devShell;
|
||||||
};
|
};
|
||||||
|
|||||||
139
hosts/uconsole/configuration.nix
Normal file
139
hosts/uconsole/configuration.nix
Normal file
@@ -0,0 +1,139 @@
|
|||||||
|
{ config, lib, pkgs, paths, self, keys, inputs, ... }:
|
||||||
|
|
||||||
|
{
|
||||||
|
# --- CORE HARDWARE (CM5 / RPi5) ---
|
||||||
|
imports = [
|
||||||
|
inputs.nixos-uconsole.nixosModules.uconsole
|
||||||
|
inputs.nixos-hardware.nixosModules.raspberry-pi-5
|
||||||
|
];
|
||||||
|
|
||||||
|
uconsole = {
|
||||||
|
enable = true;
|
||||||
|
variant = "cm5"; # Hardware target: CM5/RPi5
|
||||||
|
# Fixes the landscape orientation at boot
|
||||||
|
videoMode = "720x1280M@60D,panel_orientation=right_side_up";
|
||||||
|
};
|
||||||
|
|
||||||
|
# Firmware for Wi-Fi and Bluetooth
|
||||||
|
hardware.enableRedistributableFirmware = true;
|
||||||
|
hardware.raspberry-pi."5".apply-overlays-dtmerge.enable = true;
|
||||||
|
|
||||||
|
# Enable GPU acceleration (VideoCore VII)
|
||||||
|
hardware.graphics.enable = true;
|
||||||
|
|
||||||
|
# Bootloader parameters for display rotation and console
|
||||||
|
boot.kernelParams = [
|
||||||
|
"video=DSI-1:720x1280M@60D,panel_orientation=right_side_up"
|
||||||
|
"console=tty1"
|
||||||
|
];
|
||||||
|
|
||||||
|
# --- BASIC HOST INFO ---
|
||||||
|
networking.hostName = "uConsole";
|
||||||
|
networking.networkmanager.enable = true;
|
||||||
|
time.timeZone = "America/Montreal";
|
||||||
|
i18n.defaultLocale = "en_CA.UTF-8";
|
||||||
|
|
||||||
|
# --- GPS DAEMON ---
|
||||||
|
services.gpsd = {
|
||||||
|
enable = true;
|
||||||
|
devices = [ "/dev/ttyAMA0" ]; # Default port for RPi5/CM5 GPS
|
||||||
|
nowait = true;
|
||||||
|
};
|
||||||
|
|
||||||
|
# --- USER CONFIGURATION ---
|
||||||
|
users.users.thierry = {
|
||||||
|
isNormalUser = true;
|
||||||
|
description = "Thierry";
|
||||||
|
extraGroups = [
|
||||||
|
"wheel" # Sudo
|
||||||
|
"dialout" # Access to serial/HAM rigs
|
||||||
|
"plugdev" # Access to USB SDRs
|
||||||
|
"wireshark" # Packet capture without root
|
||||||
|
"video" # Hardware acceleration access
|
||||||
|
"networkmanager"
|
||||||
|
];
|
||||||
|
openssh.authorizedKeys.keys = [
|
||||||
|
keys.users.gortium.main
|
||||||
|
keys.users.gortium.gitea
|
||||||
|
];
|
||||||
|
};
|
||||||
|
|
||||||
|
# --- INTERFACE (WAYLAND/SWAY) ---
|
||||||
|
# Sway is recommended for the uConsole's low resources
|
||||||
|
programs.sway = {
|
||||||
|
enable = true;
|
||||||
|
extraOptions = [ "--unsupported-gpu" ]; # Often needed for RPi
|
||||||
|
};
|
||||||
|
|
||||||
|
# --- SOFTWARE TOOLKITS ---
|
||||||
|
environment.systemPackages = with pkgs; [
|
||||||
|
# Base Tools (for your Doom Emacs environment)
|
||||||
|
emacs-pgtk # Emacs with Wayland support
|
||||||
|
git # Required for Doom Emacs / Flakes
|
||||||
|
ripgrep # Fast searching for Emacs/CLI
|
||||||
|
fd # Better find for Emacs
|
||||||
|
htop # Resource monitor
|
||||||
|
tmux # Terminal multiplexer
|
||||||
|
neovim # Alternative editor
|
||||||
|
|
||||||
|
# HAM RADIO (Digital Modes)
|
||||||
|
js8call # Weak-signal keyboard messaging
|
||||||
|
wsjtx # FT8, JT65, etc.
|
||||||
|
fldigi # Digital modem (PSK, RTTY)
|
||||||
|
pat # Winlink client (Use 'pat configure' after install)
|
||||||
|
direwolf # Software TNC for APRS
|
||||||
|
chirp # Radio programming
|
||||||
|
hamlib # Rig control (rigctl)
|
||||||
|
trustedqsl # LotW log signing
|
||||||
|
|
||||||
|
# SDR + RF ANALYSIS
|
||||||
|
sdrpp # Modern SDR GUI (Best for uConsole)
|
||||||
|
gqrx # Classic SDR receiver
|
||||||
|
rtl-sdr # Drivers for RTL2832U
|
||||||
|
inspectrum # Offline signal analysis
|
||||||
|
soapysdr-with-plugins # Hardware abstraction layer
|
||||||
|
|
||||||
|
# LORA, MESH & RETICULUM
|
||||||
|
meshtastic # CLI tools for Meshtastic nodes
|
||||||
|
reticulum-network-stack # The RNS stack (rnsd, rnsh)
|
||||||
|
nomadnet # Reticulum browser/messaging
|
||||||
|
lxmf # Lightweight Mesh Exchange Protocol
|
||||||
|
sidechannel-rns # Visual UI for Reticulum communication
|
||||||
|
|
||||||
|
# HACKING & SECURITY (Kali-like suite)
|
||||||
|
nmap # Port scanning
|
||||||
|
metasploit # Exploitation framework
|
||||||
|
aircrack-ng # Wi-Fi auditing
|
||||||
|
kismet # Wireless sniffer (Essential for your Pi Zero project)
|
||||||
|
bettercap # MITM and network attack tool
|
||||||
|
wireshark # Protocol analyzer
|
||||||
|
burpsuite # Web vulnerability scanner
|
||||||
|
hashcat # Password recovery
|
||||||
|
john # John the Ripper (password cracking)
|
||||||
|
sqlmap # Automated SQL injection
|
||||||
|
|
||||||
|
# GPS & OFFLINE MAPPING
|
||||||
|
foxtrotgps # Lightweight map viewer (Perfect for small screens)
|
||||||
|
viking # GPS data editor and map viewer
|
||||||
|
gpsbabel # GPS data conversion
|
||||||
|
marble # KDE Virtual Globe (supports offline tiles)
|
||||||
|
];
|
||||||
|
|
||||||
|
# Udev rules for SDR and Radio hardware access
|
||||||
|
services.udev.packages = [
|
||||||
|
pkgs.rtl-sdr
|
||||||
|
pkgs.librtlsdr
|
||||||
|
];
|
||||||
|
|
||||||
|
# Enable Wireshark privilege separation
|
||||||
|
programs.wireshark.enable = true;
|
||||||
|
|
||||||
|
# Enable OpenSSH
|
||||||
|
services.openssh = {
|
||||||
|
enable = true;
|
||||||
|
settings.PermitRootLogin = "prohibit-password";
|
||||||
|
};
|
||||||
|
|
||||||
|
# System state version
|
||||||
|
system.stateVersion = "23.11";
|
||||||
|
}
|
||||||
30
hosts/uconsole/hardware-configuration.nix
Normal file
30
hosts/uconsole/hardware-configuration.nix
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{ config, lib, pkgs, modulesPath, ... }:
|
||||||
|
|
||||||
|
{
|
||||||
|
imports =
|
||||||
|
[ (modulesPath + "/installer/scan/not-detected.nix")
|
||||||
|
];
|
||||||
|
|
||||||
|
boot.initrd.availableKernelModules = [ "xhci_pci" "usbhid" "sdhci_pci" ];
|
||||||
|
boot.initrd.kernelModules = [ ];
|
||||||
|
boot.kernelModules = [ ];
|
||||||
|
boot.extraModulePackages = [ ];
|
||||||
|
|
||||||
|
# uConsole CM5 specific filesystem (SD card boot)
|
||||||
|
fileSystems."/" =
|
||||||
|
{ device = "/dev/disk/by-label/NIXOS_SD";
|
||||||
|
fsType = "ext4";
|
||||||
|
options = [ "noatime" ];
|
||||||
|
};
|
||||||
|
|
||||||
|
fileSystems."/boot" =
|
||||||
|
{ device = "/dev/disk/by-label/FIRMWARE";
|
||||||
|
fsType = "vfat";
|
||||||
|
};
|
||||||
|
|
||||||
|
swapDevices = [ ];
|
||||||
|
|
||||||
|
# uConsole CM5 is ARM64
|
||||||
|
nixpkgs.hostPlatform = lib.mkDefault "aarch64-linux";
|
||||||
|
hardware.enableRedistributableFirmware = true;
|
||||||
|
}
|
||||||
@@ -18,5 +18,9 @@
|
|||||||
gitea = "";
|
gitea = "";
|
||||||
bootstrap = "age1r796v2uldtspawyh863pks74sd2pwcan8j4e4pjzsvkmr3vjja9qpz5ste";
|
bootstrap = "age1r796v2uldtspawyh863pks74sd2pwcan8j4e4pjzsvkmr3vjja9qpz5ste";
|
||||||
};
|
};
|
||||||
|
# uConsole CM5 - key to be generated on first boot
|
||||||
|
uconsole = {
|
||||||
|
main = "";
|
||||||
|
};
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user