# ollie Architecture
## Philosophy
ollie's design philosophy is Plan 9 / Acme / Unix: a small substrate that integrates with the surrounding system rather than trying to do everything itself. The Go runtime (`agent.Agent`) defines what an agent *is* — an event loop, a backend connection, a message history, and three built-in primitives (`shell`, tool registry, skill registry). Everything else — orchestration, scheduling, workflows, UIs — is pushed out to external tools, scripts, and frontends.

The key difference from the Emacs model: Emacs extensibility means building capabilities *on top of* its Lisp interpreter and text primitives. Ollie's extensibility means **not** building capabilities into the core at all — instead, the core provides integration surfaces (9P filesystem, agent loop) and lets the surrounding system handle everything else. This is the Acme approach: a lightweight framework that delegates to external programs via a shared filesystem namespace.
The primary integration philosophy is Plan 9's "everything is a file." `olliesrv` exposes agent state and behaviors as files in a 9P namespace. Any program that can read and write files can drive an agent: shell scripts, editors, web apps, cron, containers.
All clients communicate via 9P exclusively. Desktop notifications use D-Bus directly (org.freedesktop.Notifications) for elevation prompts only — this is the last remaining D-Bus dependency.
Design principles:
- **Small extensible core.** The agent runtime is minimal; capabilities come from composing external scripts.
- **Zero built-in tools.** No tools are compiled into the Go binary. Every tool — including `shell` and `reasoning_think` — is an external script loaded dynamically via the 9P filesystem. The core is pure coordination: stream LLM → dispatch tool calls → loop.
- **One integration path: 9P filesystem. Streaming via blocking reads. No polling.
- **9P namespace declared via EDSL.** The entire filesystem is a single recursive `FsNodeDecl` tree in `fs/spec.go`, validated and built by `BuildTree()` in `fs/builder.go`. Adding a file means adding a `Leaf()` call — no manual stat/readdir/write wiring.
- **No framework lock-in.** Frontends are decoupled via whichever interface they prefer; the core doesn't know or care.
## Repository Structure
Single Go module (`ollie`) with one Git submodule (`kde/`) for the KDE frontend:
```
ollie/
├── agent/           Agent loop, history, hooks, prompt resolution, commands
├── backend/         LLM providers (Anthropic, OpenAI, Ollama, Gemini, Copilot, CodeWhisperer)
├── toolsrv/         Tool server: sandboxed execution, tool registry, skill management
├── session/         Session lifecycle (config, creation, persistence)
├── fs/              9P filesystem: EDSL spec + handlers (flat package)
│   ├── spec.go          Namespace declaration (single source of truth)
│   ├── fsnode.go        FsNodeDecl type + Dir/Leaf/TemplateDir constructors
│   ├── builder.go       BuildTree — spec -> *Tree wiring
│   ├── rootfiles.go     Root-level handlers (backends, models, eventwait, complete, generate, route)
│   ├── sessionfiles.go  Session-level handlers (env, ctl, plan, agent/, ...)
│   ├── agentfiles.go    Agent-level handlers (prompt, chat, state, cfg, ...)
│   ├── elevatefiles.go  Elevation handlers (policy, pending)
│   ├── procfiles.go     Process handlers
│   ├── lifecycle.go     Session create/kill/rename/shutdown + event ring
│   ├── newroot.go       NewRoot — tree construction + persistence restore
│   ├── persist.go       Session persistence to disk
│   ├── types.go         Session/AgentLog types
│   ├── tree.go          9P *Tree (from fs package)
│   ├── fs.go            9P File/FileConfig implementations
│   └── format.go        Event formatting helpers
├── detach/          Background process management (ring buffer, signal)
├── elevate/         Elevation broker (privilege escalation daemon)
├── sandbox/         Landlock sandbox config YAML
├── env/             Environment variable loading
├── log/             Structured logging
├── paths/           XDG path resolution
├── cmd/             Binaries:
│   ├── olliesrv/        9P server
│   ├── ollie-9p/        9P client
│   └── ollie-remote/    Remote execution server
├── kde/             KDE integration (submodule) — standalone GUI, Kate plugin, KRunner
├── data/agents/     Agent config JSONs (default, coding, orchestrator, worker, ...)
├── data/prompts/    Prompt templates (markdown)
├── data/tools/      Tool scripts + .meta sidecar files
├── data/skills/     Domain knowledge modules (markdown)
├── data/scripts/    Helper scripts (ollie-remount, o)
├── data/services/   Systemd/xdg-autostart service files
├── prompts/         Embedded prompt templates (compiled into binary)
└── doc/             Documentation
```
## System Overview
```mermaid
flowchart TB
    subgraph Frontends["Frontends"]
        ACME["acme (Plan 9)"]
        ELLIE["ellie (Emacs)"]
        KDE["KDE GUI / Kate / KRunner"]
        SH["o (terminal CLI / tmux TUI)"]
        HTTP["curl / scripts"]
    end
    subgraph Integration["Integration Layer"]
        direction LR
        P9["9P Filesystem\n(ollie-9p client)"]
    end
    subgraph Server["olliesrv"]
        direction TB
        NS["9P Namespace\nEDSL-declared in fs/spec.go"]
    end
    subgraph Core["Agent Engine (per session)"]
        LOOP["Agent Loop\n(agent/loop.go)"]
        SESS["Session State\n(agent/history.go)"]
        TRV["toolsrv.Server\n· dynamic tool dispatch\n· landlock sandboxed execution\n· remote execution via SSH"]
    end
    subgraph Backends["LLM Backends"]
        OLLAMA["Ollama"]
        OPENAI["OpenAI / OpenRouter"]
        ANTHROPIC["Anthropic"]
        GEMINI["Gemini"]
        CW["CodeWhisperer"]
    end
    SH --> P9
    ACME --> P9
    ELLIE --> P9
    KDE --> P9
    HTTP --> P9
    P9 --> NS
    NS --> LOOP
    LOOP <--> SESS
    LOOP --> TRV
    LOOP <--> Backends
    TRV --> Tools["tool scripts\n(OLLIE_TOOLS_PATH)\n· shell, reasoning_think\n· file_read, file_write\n· lsp_*, memory_*\n· gui_*, subagent_*"]
    TRV --> Remote["ollie-remote (SSH)\npure 9P RPC\nno embedded tools"]
```
## Core Library
The core is a single Go module (`ollie`) with no binary. Binaries live in `cmd/`.
### Package Layout
| Package | Purpose |
|---|---|
| `agent/` | Agent struct, loop, history, compaction, hooks, commands, prompt resolution, state |
| `backend/` | Backend interface + LLM providers (Anthropic, OpenAI, Ollama, Gemini, Copilot, CodeWhisperer) |
| `toolsrv/` | Tool server: dynamic tool dispatch, sandboxed execution, result tiering, remote execution (ollie-remote) |
| `session/` | Session lifecycle, config, persistence |
| `detach/` | Background process management (ring buffer, signal) |
| `elevate/` | Elevation broker (privilege escalation daemon, policy) |
| `sandbox/` | Landrun sandbox configuration and command wrapping |
| `env/` | Session environment helpers |
| `log/` | Structured logging |
| `paths/` | XDG path resolution |
### Key Types
**`agent.Agent`** — the concrete struct frontends drive:
```go
type Agent struct {
    // unexported fields — no public interface
}
func New(cfg AgentConfig) *Agent
func (a *Agent) Submit(ctx context.Context, input string)
func (a *Agent) Interrupt(cause error) bool
func (a *Agent) Queue(prompt string)
func (a *Agent) State() string
func (a *Agent) WaitChange(ctx context.Context, field, current string) (string, bool)
func (a *Agent) Close()
// ... model/backend info, CWD, usage, cost, etc.
```
**`backend.Backend`** — LLM provider contract:
```go
type Backend interface {
    ChatStream(ctx context.Context, messages []Message, tools []Tool, params GenerationParams) (<-chan StreamEvent, error)
    Name() string
    Model() string
    SetModel(model string)
    ContextLength(ctx context.Context) int
    Models(ctx context.Context) []string
}
```
**`toolsrv.Runner`** — minimal tool execution interface:
```go
type Runner interface {
    ListTools() ([]ToolInfo, error)
    CallTool(ctx context.Context, tool string, args json.RawMessage) (json.RawMessage, error)
}
```
**`toolsrv.Server`** — the concrete tool server (implements Runner):
```go
type Server struct { /* ... */ }
```
### Agent Loop (`agent/loop.go`)
The loop is the heart of the system. On each turn:
1. **Stream** — call `backend.ChatStream()` with messages + tool definitions
2. **Dispatch** — if the model returns tool calls, execute them via `toolsrv.Server`
3. **Update** — append assistant message + tool results to session history
4. **Repeat** — loop until the model produces a final text response (no tool calls)
Safety mechanisms:
- **Consecutive error limits**: soft nudge at 5, hard abort at 10
- **Replan gate**: after 8 rounds without a PLAN: block, inject a replan nudge
- **Stall detection**: 5 rounds with unchanged LastAction triggers a nudge
- **Max steps**: configurable per-agent; soft exit when reached
- **Transient retry**: up to 3 retries with exponential backoff for rate limits and 5xx
- **Context overflow**: triggers automatic compaction and retry
### Session & Context Management (`agent/history.go`)
`History` owns the message history as a flat `[]backend.Message` slice. Key behaviors:
- **TaskState**: structured JSON overlay (objective, plan_step, constraints, last_action, next_decision) injected at the top of every turn
- **Compaction**: three-zone strategy when context reaches 50% of model limit:
  - **Cold zone**: structured task state summary
  - **Warm zone**: one-line decision index (10 messages)
  - **Hot zone**: last 8 messages verbatim
- **Result tiers**: tool results classified as Hot (verbatim), Warm (summarized on compaction), or Cold (immediately collapsed)
- **Persistence**: sessions saved as JSON to `{sessionsDir}/{id}.json`
### Hooks (`agent/hooks.go`)
Lifecycle callbacks executed as shell commands with JSON payload on stdin:
| Hook | When | Exit codes |
|---|---|---|
| `agentSpawn` | Session creation | 0=ok, 2=block |
| `preTurn` | Before each turn (deprecated) | 0=inject stdout, 2=block |
| `postTurn` | After each turn | 0=ok |
| `preTool` | Before each tool call | 0=ok, 2=block execution |
| `postTool` | After each tool call | 0=append, 2=replace result |
| `preCompact` | Before compaction | 0=ok |
| `postCompact` | After compaction | 0=ok |
| `turnError` | On backend error | 0=handled (skip retries) |
### Prompt Resolution (`agent/prompt_resolver.go`)
Agent configs declare prompts as a JSON array of shell commands. Each command is executed with `$OLLIE` and `$PWD` available; stdout is concatenated to form the system prompt. This enables dynamic, composable prompts assembled from template fragments.
## 9P Server (`cmd/olliesrv/`)
`olliesrv` is the central daemon. It implements a 9P2000 file server that exposes the entire agent namespace:
### Namespace Layout
```
/                          ← root (owned by system user)
├── backends               backends list
├── help                   help text
├── models                 model list (cached)
├── agents                 agent config list
├── tools                 global tool catalog (all discoverable tools on disk)
├── ctl                    root control (invalidate, kill)
├── eventwait              global event stream (blocking read)
├── complete               request-response: code completion
├── generate               request-response: one-shot LLM generation
├── route                  request-response: model routing
├── elevate/
│   ├── policy             global elevation policy
│   └── pending/{id}       pending elevation requests (approve/deny/persist)
└── session/
    ├── new                write key=value to create session
    ├── idx                session index (one line per agent)
    ├── {name}/
    │   ├── env            session environment variables
    │   ├── ctl            session control (kill, save, invalidate)
    │   ├── plan           session-scoped markdown checklist
    │   ├── id             immutable session UUID
    │   ├── name           mutable session name (write to rename)
    │   ├── elevate        per-session elevation policy
    │   └── agent/
    │       ├── new        write config to create agent (rdwr)
    │       └── {aid}/
    │           ├── prompt        submit a prompt
    │           ├── prompt.prev   last submitted prompt
    │           ├── fifo.in       queue a prompt
    │           ├── fifo.out      pop queued prompt
    │           ├── chat          streaming chat log (blocking read)
    │           ├── log           last 64KB of chat (non-blocking)
    │           ├── state         current state (idle/thinking/calling)
    │           ├── statewait     blocking read until state changes
    │           ├── cfg           agent config (key=value)
    │           ├── ctl           agent control (stop, compact, ...)
    │           ├── cwd           working directory
    │           ├── id            immutable agent UUID
    │           ├── name          mutable agent name
    │           ├── offset        byte offset after last user prompt
    │           ├── usage         token usage stats
    │           ├── cost          estimated cost
    │           ├── ctxsz         context size
    │           ├── models        available models
    │           ├── systemprompt  rendered system prompt
    │           ├── context       rendered context window
    │           ├── tail          exec helper for tailing chat
    │           ├── tools         tool management (read = list loaded, write name = load)
    │           └── proc/{pid}    detached process output
```
### 9P Interaction Model
All agent interaction uses the `ollie-9p` client, which auto-discovers the server via `$NAMESPACE` and identifies the caller via `$OLLIE_UNAME`. The 9P filesystem exposes session state, control, tool management, and inter-agent communication as files:
- Sessions are directories under `session/`
- Session creation is a two-step process: `session/new` (name only) then `session/{name}/agent/new` (full config)
- Sessions and agents have **immutable UUIDs** (`id` file) and **mutable human-readable names** (`name` file); writing to `name` renames the entry
- **Tool loading is a file write** — writing a tool name to `agent/{id}/tools` loads it for the agent; reading it lists currently loaded tools
- **Global tool catalog** at `/tools` lists all discoverable tools on disk
- Prompts, state, chat history, and config are readable/writable files
- Streaming via blocking reads: `chat`, `statewait`, `eventwait` block the 9P read until data arrives
- Permission enforcement uses 9P user principals
- The entire namespace is declared as a single EDSL tree in `fs/spec.go` — see `doc/edsl.md`
### Permission Model (`fs/spec.go`)
Permissions are declared inline in the EDSL spec via `mode` and `GID()` options. There is no separate permission registry — the spec is the source of truth:
- `prompt` is mode `0666` — group+other can write, owner (the agent) cannot
- `chat` is mode `0444` — read-only for everyone
- `ctl` is mode `0666` — anyone can send control commands
- `plan` is mode `0666` — readable by peer agents
- `eventwait` is `0444` — blocking read for global event stream
- `session/new` is `0666` with `Request` handler — anyone can create sessions
- Ownership inherits: empty `UID`/`GID` values inherit from parent node, all the way up to root
### Session Management (`fs/`)
The `*fs.Tree` IS the session collection. Package functions manage lifecycle:
- `NewRoot(cfg)` — create the root tree from the EDSL spec (`fs/spec.go` → `BuildTree` → wired `*Tree`)
- `Lookup(tree, id)` — find a session by ID
- `All(tree)` — list all sessions
- `CreateFromRoot(tree, args)` — create a new session (two-step: session name, then agent creation)
- `KillFromRoot(tree, id)` — kill a session
- `RenameFromRoot(tree, old, new)` — rename a session
- `Shutdown(tree)` — clean shutdown (interrupt all, wait for idle, persist, close)

Event streaming uses a global ring buffer (`eventRing`) with a global `/eventwait` file. Events carry prefixes (`S` for session, `A` for agent) with structured descriptions (`new`, `kill`, `rename`). Frontends block on `/eventwait` and receive delta events without polling.