opensymphony 1.4.0

A Rust implementation of the OpenAI Symphony orchestration design
Documentation

OpenSymphony

OpenSymphony is a Rust implementation of the OpenAI Symphony specification for orchestrating AI coding agents. It connects to Linear for issue tracking and uses OpenHands as the agent runtime.

OpenSymphony TUI showing issue state, recent events, workspace details, and conversation activity

What is OpenSymphony?

OpenSymphony automates software development workflows by:

  1. Polling Linear for issues in active states (Todo, In Progress, etc.)
  2. Creating isolated workspaces for each issue with lifecycle hooks
  3. Dispatching AI agents via OpenHands to work on issues autonomously
  4. Managing retries, reconciliation, and cleanup based on issue state changes
  5. Providing a terminal UI (FrankenTUI) for monitoring and operator control

Key Features

  • Hierarchy-aware scheduling: Parent issues wait for sub-issues to complete
  • WebSocket-first runtime: Real-time agent updates with REST reconciliation
  • Per-issue workspaces: Deterministic, isolated directories with lifecycle hooks
  • GraphQL-only Linear integration: Agent-side Linear reads and writes through checked-in helper/query assets
  • Conversation reuse policies: Default per-issue reuse with optional fresh-per-run resets
  • Local-first MVP: Trusted-machine deployment with optional hosted mode

OpenSymphony 1.0.0 is the compatibility boundary for the GraphQL-only Linear rewrite. See Migration Guide if you are upgrading an older setup.

Packaging note: crates.io exposes a single public package, opensymphony. Internally, the repo still keeps clear subsystem boundaries under crates/opensymphony-*, but those directories are now internal module trees, not separately published crates.

Quick Start

Prerequisites

  • Rust toolchain (stable)
  • Python 3.12+ with uv for OpenHands server
  • Linear API key (for tracker integration)
  • LLM API key (any LiteLLM-compatible provider: OpenAI, Anthropic, Fireworks, etc.)

For platform-specific Rust and Python/uv setup steps, see Prerequisites.

Installation

cargo install opensymphony

OpenSymphony manages a local OpenHands agent-server; install the pinned runtime like this:

opensymphony install openhands

To refresh the installed CLI later, run:

opensymphony update

When you run opensymphony update from a target-repo root that already has WORKFLOW.md and config.yaml, it also refreshes the template-managed .agents/skills/ tree without rerunning the full init flow.

Required Environment

Before running opensymphony run, add the required tracker and OpenHands secret values to your shell startup file, such as ~/.zshrc or ~/.bashrc:

export LINEAR_API_KEY="lin_api_..."
export OH_SECRET_KEY='any-random-key'

Use your real Linear API key for LINEAR_API_KEY. OH_SECRET_KEY can be any random secret string for the local OpenHands runtime.

Also export your provider settings for the OpenHands conversation agent:

export LLM_MODEL="openai/accounts/fireworks/models/glm-5p1"
export LLM_API_KEY="fw-..."
export LLM_BASE_URL="https://api.fireworks.ai/inference/v1"

These LLM_* variables are required unless your target repo's WORKFLOW.md has been customized to resolve the LLM configuration some other way.

Bootstrap A Target Repo

Bootstrap the target repository in place:

cd /path/to/target-repo
opensymphony init

opensymphony init guides the bootstrap flow, customizes WORKFLOW.md, and can optionally scaffold automated code review via the OpenHands PR Review Plugin, including GitHub setup through gh when it is installed and authorized for the target repo. It also ensures .gitignore contains .opensymphony* so local OpenSymphony state stays out of version control.

For an existing target repo, opensymphony update is the lighter-weight maintenance path: it refreshes changed or new template-owned skill files under .agents/skills/ without touching WORKFLOW.md, AGENTS.md, or the broader bootstrap files.

Running the Orchestrator

Then start from the target repository:

cd /path/to/target-repo
opensymphony run

For real-time monitoring while the orchestrator is running, run the TUI in a separate terminal window:

opensymphony tui

Further Details

For generated files, environment variables, config.yaml, and the template repo details behind init, see Configuration.

For alternate config paths, debug, rehydrate, packaging, and local operator workflows, see Operations.

Project Memory

OpenSymphony can preserve completed-issue knowledge as you build. Live memory capture reads Linear evidence and discovers matching GitHub PRs by default, writes private issue capsules under .opensymphony/memory/, indexes them in DuckDB, and can sync selected knowledge into public topic docs:

opensymphony memory capture COE-123 --dry-run
opensymphony memory capture COE-123
opensymphony memory brief COE-123
opensymphony memory related --area openhands-runtime
opensymphony memory sync-docs --issues COE-123 --dry-run
opensymphony linear archive --issues COE-123 --dry-run

See Project Memory for archive guards, YAML import/backfill, source schema, and the distinction between CLI commands and template-managed agent skills.

The memory index uses DuckDB's bundled build so local installs do not need a separate DuckDB system package. That choice adds compile time and binary size, but keeps the memory database portable for local-first operator workflows.

Optional troubleshooting and validation:

cd /path/to/target-repo
opensymphony doctor

To inspect the command surface, run:

opensymphony --help

Architecture

flowchart TB
    operator["Operator / CLI / TUI"]

    subgraph daemon["OpenSymphony Daemon"]
        direction TB
        orchestrator["Orchestrator Scheduler"]
        workspace["Workspace Manager"]
        control["Read-only Control Plane API<br/>GET /healthz, /api/v1/snapshot, /api/v1/events"]
        runtime["OpenHands Runtime Client<br/>(REST + WebSocket)"]
        linear_read["Linear Read Adapter"]

        orchestrator --> workspace
        orchestrator --> runtime
        orchestrator --> linear_read
        orchestrator --> control
    end

    subgraph execution["Execution Environment"]
        direction TB
        issue_ws["Per-issue Workspace"]
        agent["OpenHands Agent Runtime"]
        graphql["GraphQL Helper + Query Assets"]

        agent --> issue_ws
        agent --> graphql
    end

    linear["Linear"]
    openhands["OpenHands Agent-Server"]

    operator --> control
    workspace --> issue_ws
    runtime --> openhands
    openhands --> agent
    linear_read -->|read issues| linear
    graphql -->|agent-side writes| linear

Internal Boundaries

OpenSymphony keeps explicit internal subsystem boundaries while shipping as one installable crates.io package:

Internal module tree Responsibility
opensymphony_orchestrator Poll loop, scheduling, retries, state machine
opensymphony_linear GraphQL client for orchestrator-side Linear reads
opensymphony_memory Issue capsules, DuckDB memory index, docs sync, archive eligibility
opensymphony_openhands REST/WebSocket client for agent runtime
opensymphony_workspace Workspace lifecycle, hooks, containment
opensymphony_control Control plane API and snapshot derivation
opensymphony_tui FrankenTUI operator client
opensymphony_cli CLI entrypoints: init, run, debug, memory, linear archive, daemon (demo), tui, doctor, rehydrate

Deployment Modes

Local Supervised Mode (MVP)

The default mode for individual developers:

  • One OpenHands server subprocess managed by the daemon
  • Host filesystem access (process-level isolation)
  • Loopback-only binding
  • No auth by default
openhands:
  transport:
    base_url: http://127.0.0.1:8000

External Local Mode

For debugging or CI with a manually managed server:

openhands:
  transport:
    base_url: http://127.0.0.1:8000
    session_api_key_env: OPENHANDS_API_KEY

Hosted Remote Mode (Future)

For organizational deployment with stronger isolation:

openhands:
  transport:
    base_url: https://agent-server.example.com
    session_api_key_env: OPENHANDS_API_KEY
  websocket:
    auth_mode: header

See docs/deployment-modes.md for full details.

Workspace Lifecycle

Each issue gets a deterministic workspace:

<workspace_root>/<issue_identifier>/
├── .opensymphony/
│   ├── issue.json              # Issue metadata
│   ├── conversation.json       # Conversation registry and launch profile
│   └── openhands/
│       └── create-conversation-request.json
├── .opensymphony.after_create.json  # Hook receipt
├── <repo_files>                # Cloned repository
└── logs/                       # Execution logs

Debugging Sessions

Use opensymphony debug <issue-id> to reopen the OpenHands conversation that OpenSymphony used for that issue:

cd /path/to/target-repo
opensymphony debug COE-284

The command resolves the issue reference to its managed workspace, reads .opensymphony/conversation.json, and resumes the same conversation_id from the original working directory. The conversation registry persists the issue reference, stable OpenHands conversation ID, timestamps, transport details, and the launch profile that created the session so a missing-but-recoverable thread can be rehydrated without losing continuity.

When the workflow uses the local supervised OpenHands server, opensymphony debug targets the same configured base URL as the orchestrator. If a ready server is already listening there, the debug command reuses it; otherwise it starts a local server for the session. For the most predictable behavior, prefer the orchestrator-managed server and avoid leaving unrelated standalone openhands CLI sessions bound to the same port.

Lifecycle Hooks

  • after_create: Clone repository, setup environment
  • before_run: Pre-execution checks
  • after_run: Post-execution cleanup
  • before_remove: Final cleanup before workspace deletion

Testing

# Unit tests
cargo test

# Static validation
opensymphony doctor

# Live tests (requires OpenHands server)
OPENSYMPHONY_LIVE_OPENHANDS=1 cargo test --test live_local_suite -- --ignored --nocapture --test-threads=1

# Smoke test
./scripts/smoke_local.sh

# Live E2E test
OPENSYMPHONY_LIVE_OPENHANDS=1 ./scripts/live_e2e.sh

Documentation

Safety and Security

Local Mode: The MVP runs with process-level isolation on trusted developer machines. Agent code executes on the host filesystem. This is suitable for:

  • Solo development on trusted repositories
  • Local experimentation
  • CI on controlled runners

Hosted Mode (future): Will provide stronger isolation with container-backed workspaces and mandatory auth.

Version Pinning

OpenSymphony pins exact versions for reproducibility:

  • openhands-agent-server==1.14.0
  • openhands-sdk==1.14.0
  • Rust stable toolchain

The managed local OpenHands bundle is sourced from tools/openhands-server/ and provisioned with opensymphony install openhands.

License

LICENSE

Acknowledgments