Skip to content
CAI
Software that uses CAICheck a score

openai/symphony

64.5

Adequate · 22 September 2026

11k

lines of production code

Elixir

primary language

6

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

This system is an Elixir-based application, likely named Symphony, designed to integrate with external issue tracking services such as Asana, GitHub, GitLab, and Jira. It provides a unified interface for polling issues and exposes provider-specific REST APIs for direct agent access. The application is built on the Phoenix 1.8 web framework and is packaged as a cross-platform binary using Burrito.

Features

Add Asana, GitHub, GitLab, and Jira tracker adapters

Symphony Elixir now supports integrating with four external issue trackers: Asana, GitHub, GitLab, and Jira. This change introduces a unified \SymphonyElixir.Tracker\ behavior and specific adapter modules for each provider, allowing the system to poll for issues by state or ID. Each adapter includes a provider-native REST tool (e.g., \asana\_api\, \github\_api\, \gitlab\_api\, \jira\_rest\) that exposes direct API access to the agent, along with the necessary client implementations and configuration schemas to handle authentication and settings validation.

elixir · high confidence

Dependencies

Upgrade to Phoenix 1.8 and add Burrito release packaging

The Elixir application has been upgraded to Phoenix 1.8 (along with Phoenix Live View 1.1 and Phoenix HTML 4.2), replacing the previous web stack. Additionally, the Burrito library has been added to enable cross-platform binary packaging for macOS (ARM64/x86\_64) and Linux (ARM64/x86\_64), and the project version has been reset to 0.0.3.

(dependencies) · high confidence

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Score

  • CAI 62 → 64 (+2.8)
  • Rubric changed (rubric-2026.08.19 → rubric-2026.09.15) — scores are not directly comparable.

Lenses

  • Code Health 94 → 92 (-1.9)
  • Architecture 100 → 95 (-5.1)
  • Maturity 57 → 71 (+14.0)
  • Readiness 47 → 49 (+2.2)
  • Security 91 → 81 (-10.7)

Resolved (22)

  • Coverage not included — suite not readable by the collector
  • Dependency hygiene not measured — no supported dependency manifest was read
  • Duplicated block (10 lines × 2) (elixir/lib/symphony_elixir/orchestrator.ex)
  • Duplicated block (9 lines × 2) (elixir/lib/symphony_elixir/codex/app_server.ex)
  • High CVE: [GHSA redacted] (elixir/mix.lock)
  • High CVE: [GHSA redacted] (elixir/mix.lock)
  • High CVE: [GHSA redacted] (elixir/mix.lock)
  • High CVE: [GHSA redacted] (elixir/mix.lock)
  • High CVE: [GHSA redacted] (elixir/mix.lock)
  • LLM evaluation failed
  • Medium CVE: EEF-[CVE redacted] (elixir/mix.lock)
  • Medium CVE: EEF-[CVE redacted] (elixir/mix.lock)
  • No exposed public API
  • Test reliability not included
  • TooManyMethods: AppServer (elixir/lib/symphony_elixir/codex/app_server.ex)
  • TooManyMethods: Client (elixir/lib/symphony_elixir/linear/client.ex)
  • TooManyMethods: Orchestrator (elixir/lib/symphony_elixir/orchestrator.ex)
  • TooManyMethods: StatusDashboard (elixir/lib/symphony_elixir/status_dashboard.ex)
  • early-stage repository — too few commits for a meaningful bus factor
  • early-stage repository — too little history to judge knowledge freshness
  • …and 2 more

New (55)

  • Documentation: no installation or build instructions (README.md)
  • Documentation: no usage examples (README.md)
  • Duplicated block (11 lines × 2) (elixir/lib/symphony_elixir/asana/client.ex)
  • Duplicated block (12 lines × 2) (elixir/lib/symphony_elixir/github/client.ex)
  • Duplicated block (12 lines × 2) (elixir/lib/symphony_elixir/orchestrator.ex)
  • Duplicated block (13 lines × 2) (elixir/lib/symphony_elixir/github/adapter.ex)
  • Duplicated block (5 lines × 2) (elixir/lib/symphony_elixir/asana/client.ex)
  • Duplicated block (5 lines × 2) (elixir/lib/symphony_elixir/gitlab/client.ex)
  • Duplicated block (5 lines × 4) (elixir/lib/symphony_elixir/asana/client.ex)
  • Duplicated block (6 lines × 4) (elixir/lib/symphony_elixir/asana/agent_tool.ex)
  • Duplicated block (7 lines × 4) (elixir/lib/symphony_elixir/asana/client.ex)
  • Duplicated block (8 lines × 2) (elixir/lib/symphony_elixir/github/client.ex)
  • Duplicated block (9 lines × 2) (elixir/lib/symphony_elixir/github/client.ex)
  • Duplicated block (9 lines × 2) (elixir/lib/symphony_elixir/workspace.ex)
  • Duplicated block (9 lines × 3) (elixir/lib/symphony_elixir/asana/client.ex)
  • Duplicated block (9 lines × 4) (elixir/lib/symphony_elixir/asana/client.ex)
  • FileTooLong: config/schema.ex (elixir/lib/symphony_elixir/config/schema.ex)
  • FileTooLong: land/land_watch.py (.codex/skills/land/land_watch.py)
  • FileTooLong: linear/client.ex (elixir/lib/symphony_elixir/linear/client.ex)
  • High CVE: [GHSA redacted] (elixir/mix.lock)
  • …and 35 more

Changes since last survey

  • 4 commits — 4 feature/other, 0 fixes

By area

  • elixir/lib — 2 commits
  • .github/workflows — 1 commit
  • elixir/mix.exs — 1 commit

Notable commits

  • change: Scrub GitHub and GitLab authentication token aliases (#119)
  • change: Use Bearer authentication for GitLab API requests (#124)
  • change: chore: release Symphony 0.0.3
  • change: ci: publish nightly binaries on main pushes

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

openai/symphony was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 22 September 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit be10a1b79df723d6d7612b5651c8522704dafb2e — the exact code this score is about.
  • Scored under rubric-2026.09.15 — the same rubric and the same method as every other entry in this index.
  • Measured by watchdog.canine.dev using codehealth-analyzer preprod-821afab8930d.