From 0d7a30efc4ad00302a4f7d2a8cda2c98790e2e58 Mon Sep 17 00:00:00 2001 From: Sam Rolfe Date: Sat, 13 Jun 2026 15:05:24 +1000 Subject: [PATCH] sam-4screen-desktop 2026-6-13:15:5:24 --- .obsidian/workspace.json | 16 +- 100 inbox/test.md | 10 + .../350 AI/Pi Agent Extensions & Skills.md | 172 +++++++++--------- 3 files changed, 108 insertions(+), 90 deletions(-) create mode 100644 100 inbox/test.md diff --git a/.obsidian/workspace.json b/.obsidian/workspace.json index 11757a7..2657085 100644 --- a/.obsidian/workspace.json +++ b/.obsidian/workspace.json @@ -13,12 +13,12 @@ "state": { "type": "markdown", "state": { - "file": "300 areas/350 AI/Pi Agent Extensions & Skills.md", + "file": "100 inbox/test.md", "mode": "source", "source": false }, "icon": "lucide-file", - "title": "Pi Agent Extensions & Skills" + "title": "test" } } ] @@ -181,10 +181,10 @@ "state": { "type": "file-properties", "state": { - "file": "300 areas/350 AI/Pi Agent Extensions & Skills.md" + "file": "100 inbox/test.md" }, "icon": "lucide-info", - "title": "File properties for Pi Agent Extensions & Skills" + "title": "File properties for test" } } ], @@ -207,17 +207,18 @@ "templater-obsidian:Templater": false } }, - "active": "7066c9273c6fb936", + "active": "c431d71763a4e2d5", "lastOpenFiles": [ + "300 areas/350 AI/Pi Agent Extensions & Skills.md", + "100 inbox/test.md", + "300 areas/350 AI/Moonshot AI Launches Kimi Work, a Local Desktop Agent Reportedly Running on Kimi K2.6 With a 300-Sub-Agent Agent Swarm.md", "200 projects/210 AI Resume/Tools.md", "200 projects/210 AI Resume/Local Hybrid Vector + Graph RAG Setup.md", "200 projects/210 AI Resume/Trigger.Dev.md", "200 projects/210 AI Resume/Websites pages for AI resume.md", "200 projects/210 AI Resume/Understand Anything.md", "200 projects/210 AI Resume/multica-ai.md", - "300 areas/350 AI/Pi Agent Extensions & Skills.md", "000 daily/Daily Notes and To Do.md", - "300 areas/350 AI/Moonshot AI Launches Kimi Work, a Local Desktop Agent Reportedly Running on Kimi K2.6 With a 300-Sub-Agent Agent Swarm.md", "100 inbox/Filesystem Consolidation Plan.md", "400 resources/430 Movies Books Plays Games/Hope.md", "100 inbox/Photo Consolidation Plan.md", @@ -234,7 +235,6 @@ "300 areas/360 Dev-Ops Network Computers/Bumblebee - The Open-Source Scanner for Messy Dev Machines.md", "300 areas/360 Dev-Ops Network Computers/Untitled.md", "100 inbox/Docker Containers.md", - "100 inbox/Home Network Overview.md", "Clippings", "Untitled.canvas", "500 archive/540 Resources", diff --git a/100 inbox/test.md b/100 inbox/test.md new file mode 100644 index 0000000..c5f360e --- /dev/null +++ b/100 inbox/test.md @@ -0,0 +1,10 @@ +# Agent Integration Test + +## Test Items +- [ ] Sub-agent spawns and returns result +- [ ] Widget shows agent activity +- [ ] Background agent completes and notifies +- [ ] /agents command shows agent types + +## Dummy Data +This is a test note created on 2026-06-13 to verify the pi-subagents system works end-to-end. diff --git a/300 areas/350 AI/Pi Agent Extensions & Skills.md b/300 areas/350 AI/Pi Agent Extensions & Skills.md index 6f73c92..8895af2 100644 --- a/300 areas/350 AI/Pi Agent Extensions & Skills.md +++ b/300 areas/350 AI/Pi Agent Extensions & Skills.md @@ -30,14 +30,25 @@ aliases: [] | **ask-user-question** | `~/.agents` | `ask_user_question` — LLM presents structured multiple-choice / text questions with keyboard UI | | **video-extract** | `~/.agents` | `video_extract` — extract frames from YouTube/local video + full Gemini analysis (requires ffmpeg + yt-dlp + GEMINI_API_KEY) | | **filechanges** | `~/.agents` | `/filechanges`, `/filechanges-accept`, `/filechanges-decline` — tracks every file LLM edits/writes, diff review, revert | -| **pi-subagents** (nicopreme) | npm (global) | Spawn child Pi agents with chains, parallel execution, async dispatch. `/agents` command. Integrates with pi-prompt-template-model for delegated prompt execution | | **pi-prompt-template-model** | npm (global) | Model-switching prompt templates with frontmatter. See [[#Prompt Templates]] section below | | **pi-mcp-adapter** | npm (global) | Single proxy tool (~200 tokens) replaces hundreds of MCP tool definitions. `/mcp` command for management. Lazy server connections | | **pi-graphify** | `~/.agents` | Knowledge graph tools: build, query, path tracing, explain, watch, add, update | | **plannotator** | `~/.agents` | Interactive plan review with browser UI, annotations, code review | | **caveman** | `~/.agents` | Ultra-compressed communication mode | | **markitdown** | `~/.agents` | Convert files (PDF, Word, Excel, PPTX, images, HTML, etc.) to Markdown. Image analysis via Qwen 2.5 VL 72B on OpenRouter. | -| **smart-router** | `~/.agents` | Dynamic prompt routing + thinking levels — analyzes intent, routes to optimal model, sets thinking level per task complexity. `/lock-model` and `/unlock-model` for manual override. Triggers Headroom compression for heavy analysis/code/devops contexts. | +| **@tintinweb/pi-subagents** | npm (global) | 18 custom agent types, background agents, mid-run steering, session resume, worktree isolation, scheduling, cross-extension RPC | +| **@tintinweb/pi-tasks** | npm (global) | Task management with dependency tracking, auto-cascade, background process tracking, TaskExecute spawns subagents via RPC | +| **gentle-engram** | `~/.agents` | Memory service connecting to engram via ENGRAM_URL. Replaces memory-vault. Session capture, compaction recovery | +| **headroom-bridge** | `~/.agents` | `compress_for_agent` tool — compresses >20K chars via Headroom Docker on .13:8787. 60-95% token reduction | + + +### pi-subagents (@tintinweb) + +v0.10.2, installed globally. 18 custom agent types in `~/.pi/agent/agents/` → `~/.agents/agents/`. Tools: `Agent()`, `get_subagent_result()`, `steer_subagent()`. `/agents` command for interactive management. Features: background agents with concurrency (4 default), mid-run steering, session resume, worktree isolation, scheduling, persistent widget showing live agent status. Cross-extension RPC event bus. + +### pi-tasks (@tintinweb) + +v0.7.0, installed globally. 7 task tools: `TaskCreate`, `TaskList`, `TaskGet`, `TaskUpdate`, `TaskOutput`, `TaskStop`, `TaskExecute`. `/tasks` command. Features: dependency tracking (blocks/blockedBy), auto-cascade, background process tracking, persistent widget. `TaskExecute` spawns subagents via RPC. --- @@ -157,83 +168,16 @@ npq check --json The **npm-security** skill instructs the Pi agent to follow this workflow before any install. ---- - -## Smart Router - -The smart-router extension (`~/.agents/extensions/smart-router/`) is a **prompt interceptor** that analyzes every incoming prompt and dynamically routes it to the most appropriate model based on intent. It also sets thinking levels and triggers Headroom context compression for heavy workloads. - -### How it works - -1. Every prompt is intercepted before the agent loop starts -2. A fast model (`openrouter/free`) analyzes the intent -3. The prompt is classified into tags (read, discuss, search, devops-low, devops-high, code-analysis-low, code-analysis-high, codewrite-low, codewrite-high) -4. The router selects the optimal model + thinking level based on tag -5. For analysis/code/devops tags, large contexts (>5K tokens) are compressed via Headroom before reaching the LLM -6. Routing + compression status appears in the **footer status bar** (e.g. `🎯 devops-low → opencode-go/deepseek-v4-flash`, `📦 73%`) - -### Routing table - -| Tag | Route Key | Model | Thinking | Use case | -|-----|-----------|-------|----------|----------| -| `read`, `discuss`, `search` | `free-core` | `openrouter/free` | — | Reading docs, chat, web search | -| `devops-low` | `economy-devops` | `opencode-go/deepseek-v4-flash` | — | Simple YAML, Docker, bash | -| `devops-high` | `precision-devops` | `opencode-go/deepseek-v4-flash` | — | Complex multi-container, server crashes | -| `code-analysis-low` | `free-core` | `openrouter/free` | — | Finding bugs in short files | -| `code-analysis-high` | `context-heavy` | `openrouter/free` | — | Refactoring large codebases (262K context) | -| `codewrite-low` | `economy-code` | `opencode-go/deepseek-v4-flash` | — | Boilerplate, simple functions | -| `codewrite-high` (React) | `precision-react` | `opencode-go/deepseek-v4-pro` | `high` | Complex React/JS | -| `codewrite-high` (other) | `precision-code-high` | `opencode-go/deepseek-v4-pro` | `high` | Complex code, dense logic | -| Short prompts (<15 chars) | `router-eval` | `openrouter/free` | — | Quick responses | - -### Thinking levels - -Only set for tasks that genuinely benefit. Everything else keeps default (off): - -| Thinking Level | Tags | Effect | -|---|---|---| -| (off) | `read`, `discuss`, `search`, `devops-low`, `devops-high`, `code-analysis-low`, `code-analysis-high`, `codewrite-low` | Fast, no extended reasoning | -| `high` | `codewrite-high`, `precision-react` | Full reasoning for genuinely complex code — worth the latency and token cost | - -### Manual override - -``` -# Lock to a specific model (disables routing) -/lock-model openrouter/anthropic/claude-3.5-sonnet - -# Re-enable dynamic routing -/unlock-model -``` - -**Note on model ID format:** `/lock-model` takes `provider/model-id`. Some OpenRouter models include the provider prefix in their ID (e.g. `openrouter/owl-alpha` has `id = "openrouter/owl-alpha"`). The handler tries both `id` and `provider/id` to find the model. - -### What about `/do-*` commands? - -The `/do-*` prompt templates are **no longer needed** for model selection. The smart-router handles all routing automatically. However, `/do-img` and `/do-make-img` are still available for image analysis/generation since those use specialized tool calls rather than just model selection. - -### Configuration - -Model mappings are defined in `~/.agents/extensions/smart-router/index.ts`. To change routing, thinking, or compression behavior, edit the `MODELS`, `THINKING`, or `COMPRESS_TAGS` tables and run `/reload`. - -### Files - -| File | Purpose | -|------|---------| -| `~/.agents/extensions/smart-router/index.ts` | Extension source | -| `~/.agents/extensions/smart-router/package.json` | npm deps (headroom-ai) | -| `~/.pi/agent/extensions/smart-router/index.ts` | Synced copy | - ---- ## Headroom -Headroom is a **context compression layer** that reduces prompt token usage by 60-95% for heavy analysis/code/devops workloads. It runs as a Docker container on the server (192.168.20.13) and is selectively triggered by the smart-router. +Headroom is a **context compression layer** that reduces prompt token usage by 60-95% for heavy analysis/code/devops workloads. It runs as a Docker container on the server (192.168.20.13) and is triggered by the headroom-bridge extension. ### How it works -1. Smart-router analyzes the prompt → determines if compression is needed +1. headroom-bridge detects analysis/code/devops contexts 2. Tags `read`, `discuss`, `search` **never** trigger compression (these are fast paths) -3. For all other tags, if accumulated context exceeds ~5K tokens, the smart-router calls `compress()` +3. For all other tags, if accumulated context exceeds ~5K tokens, headroom-bridge calls `compress()` 4. Messages are sent to the Headroom proxy at `192.168.20.13:8787` 5. Headroom compresses the context (using SmartCrusher for JSON, CodeCompressor for AST, Kompress-base ML for text) 6. Compressed messages are returned and forwarded to the LLM @@ -244,14 +188,14 @@ Headroom is a **context compression layer** that reduces prompt token usage by 6 ``` Desktop (.27) Server (.13) ───────────── ──────────── -smart-router analyzes prompt headroom proxy (Docker) +headroom-bridge headroom proxy (Docker) │ │ │ if compress needed: │ - │ compress(messages) ──────────────► │ + │ compress_for_agent(content) ──────►│ │ HTTP POST 192.168.20.13:8787 │ - │ ◄────────── compressed messages │ + │ ◄────────── compressed content │ │ │ - │ send to LLM │ + │ return to agent │ │ │ │ if proxy down: pass through │ ``` @@ -265,6 +209,10 @@ smart-router analyzes prompt headroom proxy (Docker) | Context ≥ 5K tokens + analysis/code/devops tag | Compress | | Proxy unreachable | Pass through unchanged | +### headroom-bridge + +Path: `~/.agents/extensions/headroom-bridge/index.ts`. Tool: `compress_for_agent({ content })` — compresses content >20K chars via Headroom Docker on .13:8787. 60-95% token reduction. See [[#Function Calls]] for signature. + ### Management ```bash @@ -285,10 +233,17 @@ ssh 192.168.20.13 "cd /home/sam/Docker/Containers/headroom && docker compose pul | File | Purpose | |------|---------| -| `~/.agents/extensions/smart-router/index.ts` | Compression logic (`compress()` import + `context` event handler) | +| `~/.agents/extensions/headroom-bridge/index.ts` | `compress_for_agent` tool implementation | | `/home/sam/Docker/Containers/headroom/docker-compose.yml` | Docker service definition (on .13) | | `/home/sam/Docker/Containers/headroom/.env` | Environment file (on .13) | + +## engram + gentle-engram + +engram v1.16.1 runs on nixos-desktop (.13) at `~/.local/bin/engram`. Systemd user service auto-starts. Binds `127.0.0.1:7437`, accessed via SSH tunnel: `ssh -fNL 7437:127.0.0.1:7437 192.168.20.13`. + +**gentle-engram** connects via `ENGRAM_URL=http://127.0.0.1:7437`. Replaces memory-vault. Features: session capture, compaction recovery, private block redaction. + --- ## MCP Servers @@ -337,18 +292,27 @@ pi-mcp-adapter connects Pi to external services via the Model Context Protocol. - Workspace map at `~/.pi/agent/memory-vault/00-system/workspace-map.json` - Each chat folder has isolated memory (prevents sibling directory contamination) + +### models.json (Provider Routing) + +Path: `~/.pi/agent/models.json` (symlinked from `~/.agents/models.json` for Gitea). Injects OpenRouter provider routing for KV cache sharing. DeepSeek cache discount: 91.7% ($0.145/M vs $1.74/M input). Configured: deepseek, qwen, minimax, moonshotai. Mechanism: pi-core reads `model.compat.openRouterRouting` → injects `provider: { order: [...] }`. + +### subagents.json + +Path: `~/.pi/agent/subagents.json`. Configuration for pi-subagents agent types, default models, and providers. + --- ## Useful Commands | Command | What it does | |---|---| -| `/lock-model ` | Lock routing to a specific model (e.g. `openrouter/anthropic/claude-3.5-sonnet`) | -| `/unlock-model` | Re-enable dynamic prompt routing | | `/config-setup` | One-shot: creates `.pi/`, `settings.json`, memory vault in current folder | | `/config-add ext ` | Activate an extension from `~/.agents` | | `/config-add skill ` | Activate a skill from `~/.agents` | | `/config-show` | Show active extensions and skills | +| `/agents` | Interactive agent management (pi-subagents) | +| `/tasks` | Interactive task management (pi-tasks) | | `/memctx-init` | Scan folder, build initial memory pack | | `/memctx-status` | Show memory status | | `/memctx-refresh` | Re-scan and enrich memory | @@ -357,6 +321,43 @@ pi-mcp-adapter connects Pi to external services via the Model Context Protocol. | `/filechanges-decline` | Revert all changes | | `markitdown ` | Convert file to Markdown (PDF, Word, Excel, PPTX, images, HTML, etc.) | | `markitdown-vision ` | Describe image using Qwen 2.5 VL 72B via OpenRouter | +| `Agent()` | Spawn subagent (pi-subagents) | +| `get_subagent_result()` | Retrieve results from background agent | +| `steer_subagent()` | Send mid-run steering message | +| `compress_for_agent()` | Compress large content via Headroom | + + +## Agent Roster (18) + +| Agent | Model | Provider | +|-------|-------|----------| +| chat-search | google/gemini-2.5-flash:free | openrouter | +| code-analysis | deepseek-r1-distill-qwen-32b | opencode-go | +| code-ingest | google/gemini-2.5-flash:free | openrouter | +| coder-basic | deepseek/deepseek-chat | openrouter | +| coder-pro | deepseek/deepseek-v4-pro | openrouter | +| database | deepseek-r1-distill-qwen-32b | opencode-go | +| devops-basic | deepseek/deepseek-chat | openrouter | +| devops-pro | deepseek/deepseek-v4-pro | openrouter | +| document-writer | deepseek-r1-distill-qwen-32b | opencode-go | +| file-ops | qwen-coder-32b-instruct | opencode-go | +| home-automation | deepseek-r1-distill-qwen-32b | opencode-go | +| image-maker | black-forest-labs/flux-1-schnell | openrouter | +| iot-coder | qwen-coder-32b-instruct | opencode-go | +| iot-hardware | moonshotai/kimi-k2.6 | openrouter | +| obsidian | deepseek-r1-distill-qwen-14b | opencode-go | +| research | google/gemini-2.5-flash:free | openrouter | +| video-analyze | qwen/qwen-2.5-vl | openrouter | +| vscode-setup | qwen/qwen-3-coder-next | openrouter | + +## Function Calls + +``` +Agent({ subagent_type, prompt, description, model?, thinking?, max_turns?, run_in_background?, resume?, isolated?, isolation?, inherit_context? }) +get_subagent_result({ agent_id, wait?, verbose? }) +steer_subagent({ agent_id, message }) +compress_for_agent({ content }) +``` --- @@ -377,11 +378,18 @@ pi-mcp-adapter connects Pi to external services via the Model Context Protocol. ## Tasks - [x] Rebuild NixOS to activate new packages (Google provider, ffmpeg/yt-dlp, pi-prompt-template-model, pi-mcp-adapter, pi-subagents) ✅ 2026-06-11 +- [x] Migrate pi-subagents to @tintinweb version with 18 agent types +- [x] Define all 18 agent types in subagents.json +- [x] Deploy models.json with OpenRouter provider routing +- [x] Deploy engram + gentle-engram memory service on .13 +- [x] Install pi-tasks (@tintinweb/pi-tasks) v0.7.0 +- [x] Set up Zellij layout for Pi dev environment - [ ] Add MCP servers to `~/.config/mcp/mcp.json` or `.mcp.json` as needed (Home Assistant, databases, etc.) - [ ] Run `/reload` in Pi to activate filechanges and new templates - [ ] Add more prompt templates to `~/.pi/agent/prompts/` as needed - [ ] Verify video-extract works with Gemini -- [x] Add markitdown skill to Obsidian skills page -- [x] Add smart-router extension and update Obsidian docs -- [x] Deploy Headroom Docker compression on .13, integrate with smart-router +- [x] Add markitdown skill to Obsidian skills page ✅ 2026-06-11 +- [x] Add smart-router extension and update Obsidian docs ✅ 2026-06-11 +- [x] Deploy Headroom Docker compression on .13, integrate with smart-router ✅ 2026-06-11 +- [x] Replace smart-router with headroom-bridge and update all references - [ ] Clean up workspace-map.json entries for any stale memory packs