chore(deps): update ag2 requirement from ~=0.12.3 to ~=0.13.0 in /packages/benchmarks/OSWorld

[dependabot]

Updates the requirements on ag2 to permit the latest version.

Release notes

Sourced from ag2's releases.

v0.13.0

Highlights

🛣️ The Path to v1.0 — A Major Step

v0.13.0 is a significant release for our journey to V1.0. It introduces a brand-new Multi-Agent Network runtime and LiveAgent for full-duplex realtime voice. Plus, A2A v1.0 and MCP now in Beta to complete the connectivity story.

📍 Release Roadmap

🌐 Network — Multi-Agent Runtime (NEW)

Other frameworks treat an agent or a graph as the primitive. AG2 Beta makes the channel between agents the primitive — a durable, identity-scoped, protocol-typed container. Open it, work inside it, close it. The channel is the artifact.

• 🔗 Channel as the unit – Append-only event log per channel. Adapter state is derived from the log, so a hub restart is a non-event.
• 🎭 Choreography you can dial in – From open multi-party discussion to fully declared workflows, all on the same primitive. Four built-in patterns ship today:
  • consulting — 1↔1, one round (strict Q+R, auto-close)
  • conversation — 1↔1, multi-turn (bidirectional, long-running)
  • discussion — N-party turn-taking (round-robin, dynamic, or static ordering)
  • workflow — orchestrated by a declarative TransitionGraph, with conditions and dynamic handoffs (great for transitioning your classic AG2 group chats - Guidance)
• 🛠️ Design your own orchestration – The ChannelAdapter protocol is small (~50 lines for a custom adapter). Define your own manifest, state, and turn-taking rules; reuse the durability and identity layers for free.
• 🪪 Identity is three records – Passport (immutable, hub-stamped), Resume (mutable track record + observed stats), SKILL.md (LLM-facing doc). Discovery ranks by observed outcomes.
• 🤝 Federation with Passport + Visa – A channel can span two hubs the same way a TCP connection spans two networks. Cross-org channels are the base case, not an extension.
• 👤 HumanClient – Humans are peers on the network, not a special case.

🎮 Try it in the Playground – An 8-page hands-on walkthrough (~30 min) with full code examples. Build a hub, register agents, open channels, walk through all four turn-taking patterns, hub-side governance, and write your own adapter from scratch.

📔 Docs: Multi-Agent Network

🎙️ LiveAgent — Realtime Voice (NEW)

New autogen.beta.live module for full-duplex voice agents backed by provider realtime APIs. Unlike turn-by-turn STT/TTS pipelines, LiveAgent opens a single bidirectional session for the entire conversation — audio flows in and out continuously.

• 🎤 Single bidirectional session – No turn-by-turn round trips.
• 🛑 Built-in VAD and barge-in – Voice activity detection and interruption support out of the box.
• 🛠️ Same tool surface as Agent – @agent.tool decorator works identically; tool calls route through AG2's normal executor.
• 🌐 Provider-neutral – OpenAI Realtime (10 voices: alloy, ash, ballad, coral, echo, sage, shimmer, verse, marin, cedar) and Gemini Live (8 voices: Aoede, Charon, Fenrir, Kore, Leda, Orus, Puck, Zephyr).
• 📝 Text-only mode – Keep the realtime session for low-latency turn detection but disable audio output entirely.
• 🔊 Audio peers – SoundDevicePlayer and SoundDeviceRecorder share the conversation context with the agent.

📔 Docs: LiveAgent · STT & TTS alternative also available.

🔗 A2A v1.0 — Now in Beta

A2A is now available in the Beta framework via the new autogen.beta.a2a module.

• 📡 Expose any AG2 Agent over A2A via A2AServer
• 🔌 Connect to a remote A2A endpoint as if it were an LLM provider via A2AConfig
• 🚚 Transport-agnostic: JSON-RPC, HTTP+JSON (REST), or gRPC
• 📥 Tasks & push notifications for long-running work
• Install with pip install "ag2[a2a]"

... (truncated)

Commits

• 7b006e9 Version 0.13 bump and roadmap updates (#2811)
• 85ab6e4 test: Various test fixes and LLM provider/package alignments (#2812)
• a8731b8 refactor(beta): replace ToolCallEvent.provider_data with typed Gemini subclas...
• b29c011 feat: Implement SSRF protection with URL validation in document agent (#2784)
• 9b40fc1 feat(beta): introduce A2A v1.0 (#2791)
• 2f9fb57 feat(beta/knowledge): opt-out flags and observable aggregation lifecycle (#2804)
• 57d6afa feat(beta/network): adapter-owned tools + subclass surface (#2802)
• f285c66 Switch interop-pydantic-ai extra to pydantic-ai-slim (#2803)
• 88c6c95 feat(beta/network): HumanClient + observability foundation (#2801)
• 14a9505 Beta/mcp support (#2702)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

Greptile Summary

Automated dependency update bumping ag2 from ~=0.12.3 / ~=0.12.0 to ~=0.13.0 in the OSWorld benchmark package. The ag2 0.13.0 release adds a Multi-Agent Network runtime, LiveAgent for real-time voice, A2A v1.0 (Beta), and MCP support.

• requirements.txt: version constraint updated from ~=0.12.3 to ~=0.13.0.
• setup.py: version constraint updated from ~=0.12.0 to ~=0.13.0, incidentally aligning the two files which previously pinned to different patch floors.
• The OSWorld codebase includes a vendored copy of autogen under mm_agents/coact/autogen/, so the ag2 package upgrade primarily affects the benchmark environment setup rather than the local customised agent code.

Confidence Score: 5/5

Routine automated dependency bump with no logic changes; safe to merge.

Only two lines change across two files, both bumping the ag2 compatible-release constraint from 0.12.x to 0.13.x. The OSWorld benchmark uses a vendored local copy of autogen for its agent code, so the package version has limited blast radius. No API usage in the non-vendored code depends on internals that changed in 0.13.0.

No files require special attention.

Important Files Changed

Filename	Overview
packages/benchmarks/OSWorld/requirements.txt	Bumps ag2 from ~=0.12.3 to ~=0.13.0 for the OSWorld benchmark environment
packages/benchmarks/OSWorld/setup.py	Bumps ag2 installable package constraint from ~=0.12.0 to ~=0.13.0, aligning with requirements.txt

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A[requirements.txt\nag2 ~=0.12.3] -->|bump| B[requirements.txt\nag2 ~=0.13.0]
    C[setup.py\nag2 ~=0.12.0] -->|bump| D[setup.py\nag2 ~=0.13.0]
    B & D --> E[OSWorld Benchmark\nEnvironment]
    E --> F[mm_agents/coact/autogen/\nvendored autogen copy\nunaffected by package bump]

Loading

_{Reviews (5): Last reviewed commit: "Merge branch 'develop' into dependabot/p..." | Re-trigger Greptile}

[github-actions]

LifeOps Multi-Tier Benchmark

Suite: smoke — Tiers requested: large,frontier

large — SUMMARY.md missing

frontier — SUMMARY.md missing

Artifacts: lifeops-multi-tier-large-26182487637, lifeops-multi-tier-frontier-26182487637

[github-actions]

LifeOps Multi-Tier Benchmark

Suite: — Tiers requested:

large — cancelled

frontier — cancelled

Artifacts: lifeops-multi-tier-large-26199753729, lifeops-multi-tier-frontier-26199753729

[claude]

Claude encountered an error —— View job

---

I'll analyze this and get back to you.

[github-actions]

LifeOps Multi-Tier Benchmark

Suite: — Tiers requested:

large — cancelled

frontier — cancelled

Artifacts: lifeops-multi-tier-large-26200652885, lifeops-multi-tier-frontier-26200652885

[github-actions]

LifeOps Multi-Tier Benchmark

Suite: smoke — Tiers requested: large,frontier

large

LifeOps Multi-Tier Benchmark

Tier: large
Suite: smoke

frontier

LifeOps Multi-Tier Benchmark

Tier: frontier
Suite: smoke

Artifacts: lifeops-multi-tier-large-26201257593, lifeops-multi-tier-frontier-26201257593