NVIDIA-NeMo · ananthsub · Aug 6, 2026 · Aug 6, 2026
diff --git a/fern/docs.yml b/fern/docs.yml
@@ -34,6 +34,10 @@ versions:
   - display-name: Main
     path: versions/main.yml
     slug: main
+  - display-name: "0.5.0"
+    path: versions/v0.5.0.yml
+    slug: v0.5.0
+    availability: stable
   - display-name: "0.4.0"
     path: versions/v0.4.0.yml
     slug: v0.4.0

diff --git a/fern/versions/latest/pages/about/release-notes.mdx b/fern/versions/latest/pages/about/release-notes.mdx
@@ -5,7 +5,120 @@ position: 4
 ---
 
 <AccordionGroup>
-<Accordion title="v0.4.0" defaultOpen>
+<Accordion title="v0.5.0" defaultOpen>
+
+### Release Summary
+
+The NeMo Gym 0.5.0 release expands the sandbox ecosystem to seven providers, adds four new general-purpose agent harnesses (Codex, KiloCode, RemoteAgent, and Any-SWE) bringing the total to 20, adds 21 new benchmarks and environments, and wires rollout observability end-to-end from the model server boundary through agent transcripts.
+
+Highlights:
+
+- Seven sandbox providers: Docker, Daytona, ECS Fargate, Enroot, and OpenShell join OpenSandbox and Apptainer; large-scale OpenSandbox reliability significantly improved
+- Four new agent harnesses: Codex CLI, KiloCode, RemoteAgent, and `anyswe_agent`
+- Recompute rewards from stored rollouts without re-running inference with `gym eval reverify`
+- Rollout observability joined end-to-end: model-call capture, agent observations, and a standardized `ng_trajectory` schema
+- 21 new environments across six domains: Agentic, Knowledge and instruction following, Long context, Science and coding, Translation and multilingual, and Reasoning
+
+### First-Time Contributors
+
+We welcomed 22 new contributors to NeMo Gym with this release:
+
+- **@mpatel31415** added `gym eval reverify` command and `--judge-failed-only` flag for recovering failed judge rows
+- **@Glorf** added per-rollout model-call capture, Docker and ECS Fargate sandbox providers, rollout observation contract, Claude Code rollout observations, and standardized `ng_trajectory` schema
+- **@nblintao** added per-request policy endpoint override for the SWE agents, enabling RL training frameworks to route each episode through a per-episode recording proxy
+- **@JeffPengCoder** brought OSWorld — a stateful desktop GUI benchmark — into the benchmark catalog
+- **@rystewart-nvidia** added the Legal Agent Bench integration, exposing Harvey's 1,749-task LAB benchmark through standard Gym eval commands
+- **@fallintoplace** fixed the long-standing disagreement between runtime aggregate metrics and the persisted `output.jsonl`
+- **@jonathanlli** added RULER pretrain evaluation, enabling text-completion scoring for base and midtraining checkpoints
+- **@thompsonb** overhauled WMT24++ and FLORES translation evaluation (55 locales, 219 language pairs, chrF/spBLEU scoring); expanded MMLU-ProX to 29 languages
+- **@hkumar92** added the PinchBench agentic benchmark
+- **@pachmu** added ToolSandbox, IHEval, RoleMRC, and RAGTruth benchmarks
+
+Thank you to all 57 NeMo Gym contributors this cycle, including 22 first-time contributors!
+
+### Command Line Interface
+
+- **`gym eval reverify`** — re-run only the verifier on stored rollouts; `--judge-failed-only` recovers rows that failed due to a flaky judge without re-verifying successful rollouts
+- `gym list` and `gym search` extended to cover models, resources-servers, and agents; `gym list <type> <name>` drills into a single artifact
+- External plugins discoverable via `--search-dir` and environment variables; `-v/--verbose` now accepted before any subcommand
+
+### Sandboxing
+
+Five new built-in providers: **Docker**, **Daytona**, **ECS Fargate**, **Enroot**, and **OpenShell** join OpenSandbox and Apptainer. Provider choice is a one-line config swap — any agent built on `nemo_gym.sandbox` works with any provider unchanged.
+
+OpenSandbox reliability at scale is significantly improved: keepalive-bounded transport eliminates silent rollout zeroing at concurrency 300–1500; image registry auth supports private container images; sandbox resources are automatically labeled with team, user, and workload identifiers.
+
+See [Available Sandbox Providers](https://docs.nvidia.com/nemo/gym/nemo-gym/nemo_gym/sandbox/providers/) for the full list.
+
+### Configure Agent Harnesses
+
+New harnesses join the existing set (Claude Code, Hermes, mini-SWE-Agent, OpenClaw, Pi, and more):
+
+- **Codex** and **KiloCode** integrate `codex exec` and `kilo run` respectively, routing model calls through Gym for per-rollout capture
+- **`anyswe_agent`** runs any Gym harness inside a SWE task container
+- **`swe_agents`** adds OpenCode as a supported agent framework alongside OpenHands, with DeepSWE and DeNovoSWE dataset support and message replay for trajectory branching
+- **RemoteAgent** drives any external service that implements `POST /v1/responses`, with Gym owning the tool loop and verification
+
+### Configure Models
+
+- vLLM can now drive `/v1/completions` for base and pretrain checkpoint evaluation via opt-in `use_completions_api`
+- All Gym model servers now accept `stream: true` on `/v1/chat/completions` via synthesized SSE, unblocking streaming-first clients such as OpenClaw and Codex
+- Add `expose_tools_over_mcp: true` to any resources server config to serve its tools over MCP with no handler code changes
+
+### Rollout Observability
+
+- Per-rollout model-call capture records requests, responses, token usage, and latency at the model server boundary
+- Claude Code transcripts populate `ng_agent_observations`; agent observations and model-call capture are joined through a standardized `ng_trajectory` schema
+- Judge failures are routed to a `_failures.jsonl` sidecar, keeping aggregate metrics over successfully-judged rows only
+
+### New Benchmarks and Environments
+
+21 new environments across six domains:
+
+- **Agentic:** PinchBench (147 real-world tasks), OSWorld (desktop GUI with VM-backed evaluation), Legal Agent Bench (1,749 Harvey LAB tasks), ToolSandbox (Apple multi-turn tool-use), BrowseComp (web research), BioMNIBench DA, Tau3 banking (BM25+grep offline eval path)
+- **Knowledge and instruction following:** SECQUE, FinanceBench, Finance SEC Search, IHEval (instruction hierarchy, rule-based), Litmus-Bench v0.1, RoleMRC (role-play MRC), RAGTruth (hallucination detection)
+- **Long context:** NIAH (retrieval with overlap penalty)
+- **Science and coding:** CVDP Agentic (expanded to support the agentic subset, harness-agnostic)
+- **Translation and multilingual:** WMT24++ (expanded from 5 to 55 locales), FLORES (expanded from 30 to 219 language pairs, chrF/spBLEU scoring), MMLU-ProX (expanded to 29 languages); RULER now supports pretrain text-completion evaluation
+- **Reasoning:** ReasoningGym environments — six agentic variants: Claude Code, Hermes, and four LangGraph-based variants (orchestrator, reflection, parallel thinking, and ReWOO)
+
+See the [Available Environments](https://github.com/NVIDIA-NeMo/Gym#-available-environments) table for the full list.
+
+### Deprecation Notices
+
+- WMT24++ and FLORES scores from prior versions are not comparable with this version's chrF/spBLEU output
+- Python 3.13.14 is now required (previously 3.12); users running Gym in Python 3.12 environments must upgrade
+
+### Bug Fixes
+
+- SciCode realigned to the AA 65-problem test set with per-rollout subtask accuracy reporting
+- Fixed silent rollout zeros at high concurrency against OpenSandbox (keepalive-bounded transport)
+- Fixed frozen rollouts in long-running benchmarks (TCP keepalive on global aiohttp connector)
+- Fixed `gym eval run` failing with `FileNotFoundError` when the output directory did not exist
+- Fixed `tool_choice` sent to vLLM without `tools`, causing request rejection
+- Fixed Claude Code `max_turns` hardcoded to 30; `max_turns: null` now removes the cap
+- Fixed Apptainer sandbox env vars injected into subprocess argv instead of environment
+- Fixed MCQA answer parsing for wrapped formats (`$D$`, `(D)`, `\boxed{\text{Answer: G}}`)
+- Fixed aggregate metrics including non-persisted rollouts, causing disagreement with `output.jsonl`
+
+### Documentation
+
+- Rewrote the key terminology glossary with a Gym overview, component map, and links to how-to pages
+- New page documenting the Anthropic Messages dialect (`POST /v1/messages`) and wiring Claude Code through a Gym model server
+- Updated NeMo RL v0.7.0 compatibility guidance
+- Migrated all remaining docs examples from legacy `ng_run`/`ng_collect_rollouts` to the unified `gym` CLI
+- Documented `gym list` and `gym search` extensions, external plugin discovery, and MCP auto-exposure
+- Added `gym eval reverify` and multi-reward verification contract documentation
+
+### Release Assets
+
+[GitHub Release v0.5.0](https://github.com/NVIDIA-NeMo/Gym/releases/tag/v0.5.0)
+
+
+
+</Accordion>
+
+<Accordion title="v0.4.0">
 
 ### Release Summary
 

diff --git a/fern/versions/v0.5.0.yml b/fern/versions/v0.5.0.yml
@@ -0,0 +1,67 @@
+tabs:
+  docs:
+    display-name: Documentation
+    slug: ""
+  api:
+    display-name: API Reference
+    slug: api
+
+navigation:
+  - tab: docs
+    layout:
+      - folder: ./v0.5.0/pages/about
+        title: "About"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/get-started
+        title: "Get Started"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/data
+        title: "Prepare Data"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/agent-server
+        title: "Configure Agents"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/model-server
+        title: "Configure Models"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/build-verifiers
+        title: "Build Verifiers"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/evaluation
+        title: "Evaluate"
+        title-source: frontmatter
+      - section: Tutorials
+        contents:
+          - folder: ./v0.5.0/pages/training-tutorials
+            title: "Training Tutorials"
+            title-source: frontmatter
+          - folder: ./v0.5.0/pages/evaluation-tutorials
+            title: "Evaluation Tutorials"
+            title-source: frontmatter
+      - folder: ./v0.5.0/pages/environment-tutorials
+        title: "Build Environments"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/model-recipes
+        title: "Model Recipes"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/infrastructure
+        title: "Infrastructure"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/reference
+        title: "Reference"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/troubleshooting
+        title: "Troubleshooting"
+        title-source: frontmatter
+      - folder: ./v0.5.0/pages/contribute
+        title: "Contribute"
+        title-source: frontmatter
+  - tab: api
+    layout:
+      - section: API Reference
+        slug: reference/api-reference
+        contents:
+          - page: Overview
+            path: ./v0.5.0/pages/api-reference/index.mdx
+            slug: ""
+          - folder: ../product-docs/nemo-gym/Full-Library-Reference
diff --git a/fern/versions/v0.5.0/pages/about/architecture.mdx b/fern/versions/v0.5.0/pages/about/architecture.mdx
@@ -0,0 +1,126 @@
+---
+title: "Architecture"
+description: "Understand how NeMo Gym implements environments as composable server components."
+position: 2.5
+---
+
+<Info>
+
+**Goal**: Understand how NeMo Gym implements environments as composable server components.
+
+**Read first**: [Environments](/about/concepts/environments) — what an environment is and how it decomposes into dataset, agent harness, verifier, and state.
+
+</Info>
+
+## How NeMo Gym Implements Environments
+
+NeMo Gym implements environments as composable FastAPI servers that communicate over async HTTP:
+
+| Concept | NeMo Gym Component Implementation |
+|---------|---------------|
+| Dataset | JSONL: Responses API input — each row is a task (a single problem or challenge) for the agent to solve |
+| Agent Harness | FastAPI Agent Server |
+| Verifier + State | FastAPI Resources Server |
+| Model | FastAPI Model Server or managed by your own agent harness |
+
+All components are composable. Use different datasets with the same resources server, the same resources server with different models, or the same model with different agent harnesses.
+
+This gives you flexibility to integrate with your existing models and agents:
+
+- **Bring your own agent** — Integrate your existing agent to use it with any Gym environment components.
+- **Use a built-in agent** — NeMo Gym includes some native agents, e.g. general-purpose multi-step tool calling, as well as built-in integrations with external harnesses like OpenHands.
+- **Train with any model endpoint** — The Model Server standardizes different LLM endpoints behind the Responses API and provides token IDs and log probabilities needed for RL training.
+
+## How an Agent Runs a Task in NeMo Gym Environments
+
+Each task attempt flows through three steps. The resulting trajectory is called a *rollout*:
+
+1. **Initialize** — The agent receives a task row from the dataset and initializes a session on the Resources Server, which sets up isolated state for this task.
+2. **Agent Loop** — The agent calls a model for inference, then routes any tool calls to either its own tools or the Resources Server. This repeats until the agent decides the task is complete.
+3. **Verify** — The agent asks the Resources Server to score the attempt. The verifier inspects the final state and returns a reward signal.
+
+
+```
+  Dataset (JSONL - one row per task)
+       │
+       ▼
+┌──────────────────────────────────────────┐
+│               Agent Server               │
+│                                          │
+│  run():                                  │
+│    1. resources.seed_session()  ─────────────►  Resources Server
+│    2. agent loop:                        │
+│         model.responses()       ─────────────►  Model Server
+│         resources.my_tool()     ─────────────►  Resources Server
+│    3. resources.verify()        ─────────────►  Resources Server
+└──────────────────────────────────────────┘
+
+┌───────────────────────────┐   ┌────────────────────────────────────┐
+│       Model Server        │   │        Resources Server            │
+│                           │   │                                    │
+│  responses():             │   │  seed_session(): init env state    │
+│    → text, tool calls,    │   │  my_tool():      execute action    │
+│      or code              │   │  verify():       evaluate → reward │
+└───────────────────────────┘   └────────────────────────────────────┘
+```
+
+
+## Server Types
+
+### Agent Server
+
+Hosts agent harnesses that orchestrate rollouts. Use your own harness, or use built-in harnesses such as OpenHands or NeMo Gym's native harnesses such as Simple Agent.
+
+### Model Server
+
+A stateless LLM inference endpoint that standardizes different model providers behind the Responses API. Supports local inference and inference providers.
+
+### Resources Server
+
+Manages environment-specific tools, per-task state isolation, and verification:
+
+- **Environment-Specific Tools** — capabilities the environment provides to any agent (e.g., code execution, database queries, API calls)
+- **State Isolation** — each rollout gets its own session, so attempts never interfere with each other. Environments range from lightweight (verify a math answer, no setup needed) to heavyweight (provision a Docker container with a specific repo checkout for SWE-Bench-style tasks).
+- **Verification** — scoring logic that evaluates the agent's output and returns a reward
+
+## Where Tools Live
+
+Tools exist on a spectrum — some belong to the agent and can be used with any environment, some belong to the environment and can be used with any agent:
+
+- **Agent-specific tools** are part of the agent harness. They're capabilities the agent brings regardless of which environment it runs in (e.g., OpenHands brings file editing and terminal tools).
+- **Environment-specific tools** are part of the Resources Server. They're capabilities the environment provides to any agent that connects (e.g., a `run_tests` endpoint, a database query tool, a sandbox execution API).
+
+An agent can use both simultaneously — its own tools and the environment's tools in the same task. NeMo Gym's server split reflects this: agent-specific logic in the harness, environment-specific logic in the Resources Server.
+
+## Communication
+
+Servers communicate over async HTTP (aiohttp) with:
+- **Session cookies** propagated through the call stack for stateful environments
+- **Retry logic** with exponential backoff (3 attempts)
+- **Connection pooling** via a singleton aiohttp client for high-concurrency workloads
+
+## Next Steps
+
+<Cards>
+
+<Card title="Concepts" href="/about/concepts">
+Understand environments, evaluation, and training before diving into implementation.
+</Card>
+
+<Card title="Browse Environments" href="https://github.com/NVIDIA-NeMo/Gym#-available-environments">
+Browse available environments for evaluation and training.
+</Card>
+
+<Card title="Agents" href="/agent-server">
+Explore available agent harnesses and learn how to integrate your own agent.
+</Card>
+
+<Card title="Training" href="/tutorials/training-tutorials">
+Improve your agent or model with RL or fine-tuning.
+</Card>
+
+<Card title="Build Custom Environments" href="/environment-tutorials">
+Create your own evaluation or training environments.
+</Card>
+
+</Cards>