[mpfaffenberger]

Ship a Pydantic AI agent in the agents bundle, beside Claude Code and the others, at
@local/agentenv-framework/agents/pydantic-ai (alias pydantic-ai).

The agent-env protocol SDK serves the A2A endpoint and its extensions; each turn runs a Pydantic AI
Agent in process with the Pydantic AI Harness Coder tools (shell, file tools, sub-agents) in a
LocalWorkspace, the task's MCP servers as MCPToolsets and installed skills through the harness's
Skills. A context's message history is persisted, so later turns continue it, its messages are the
live trajectory, and snapshots carry it with the files attached in it. The model is called through
the [model] endpoint as an OpenAI-compatible one; a vllm: prefix picks Pydantic AI's vLLM provider.

Pydantic AI's own Agent.to_a2a is not used: it serves plain A2A, without the agent-env extensions
the validator checks.

Also: the fake OpenAI endpoint answers streamed requests with server-sent chunks, which Pydantic AI
always asks for.

Verified: unit tests (tst/unit/agents/pydantic_ai, 34), tst/integration/cli/run_bundle_pydantic_ai_test.py (6, real Docker against the fake OpenAI endpoint), ruff check, and agent-env a2a-agent validate locally against an OpenAI-compatible vLLM endpoint: every extension the agent advertises passed (agent-config, mcp-config, trajectory, skill-config, snapshot, peer-agents, install/v1); the snapshot changelog is not implemented, as for OpenHands.

Confidence Score: 4/5

Fix the overly broad snapshot exclusion before merging.

Findings

1.  Snapshots skip project files ▶

Fix with agent prompt

### Issue 1
src/agent_env/agents/agents/pydantic-ai/pydantic_ai_agent.py:579
`_entry_holding` selects the first directory under the workspace, not just the agent's state directory. If the shipped image runs with `PYDANTIC_AI_A2A_WORKSPACE=/home`, the state lives at `/home/agent/.pydantic-ai-a2a`, but saving skips all of `/home/agent`, including project files there. Loading also leaves that whole directory unchanged. Both calls can return success without saving or restoring those files.

Exclude and preserve only the agent's state directory, not its whole ancestor.

---

For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.

Summary

Adds Pydantic AI as a bundled agent, with coding tools, MCP servers, skills, saved conversations, snapshots, and installation support.

• Pydantic AI tasks use coding tools and continue their context's conversation.
• Pydantic AI conversations and workspace files can be saved and restored.
• The Pydantic AI agent is available as a bundled, installable agent.
• The fake OpenAI endpoint sends chunks for streamed requests.

Diagram

%%{init: {'theme': 'neutral'}}%%
flowchart LR
  Task[A2A task] --> Agent[Pydantic AI agent]
  Agent --> Tools[Coding tools and MCP servers]
  Agent --> History[Saved conversation]
  History --> Snapshot[Snapshot]
  Workspace[Workspace files] --> Snapshot

Loading

_{Reviews (6) · Last reviewed commit: "fix(agents): keep the Pydantic AI agent'..." · Reviewed by Greptile}

[earakely-scale]

🤖 Automated Claude routine — Env Pod PR Context Review. This is a bot, not Edgar Arakelyan; not a human review.

Context from a sibling PR and from main, not about this diff's own logic.

#345 adds a second agent (letta-code) and lands on the same three shared registration points this PR does. Two of them are exhaustive assertions, so they don't merge additively:

• tst/unit/bundle/shipped_bundles_test.py:45 — assert {alias: … for …} == { … } over the whole alias table. This PR's expected dict is the six on main plus pydantic-ai; feat(agents): add a Letta Code agent #345's is the same six plus letta-code. Once both land the real table holds eight, so whichever expected dict survives the merge is short one entry and the test fails. It needs both names, not whichever side wins the conflict.
• src/agent_env/agents/aliases.toml — main ends at openhands = ["openhands"] and both PRs append a line after it, so that's a textual conflict either way.
• .github/scripts/infra_build.py — both add an _IMAGES entry and a _SMOKES entry; those are dict keys, so they do merge additively.

Separately, this branch looks behind main (a4ae4f6) on the third one. Your hunk for tst/unit/test_infra_images_script.py:62 shows the variable as agents and the expected list ending "agentenv-pi", "agentenv-proxy"], while main now reads:

    bundles = [image.name for image in BUNDLE_IMAGES]
    …
    assert "agentenv-gateway" in planned["infra"] and bundles == [
        "agentenv-claude-code", "agentenv-codex", "agentenv-gemini", "agentenv-opencode", "agentenv-openhands",
        "agentenv-pi", "agentenv-proxy", "agentenv-mail-mcp"]

So after a rebase the list also needs agentenv-mail-mcp, and the name is bundles. Worth noting the order is BUNDLE_IMAGES declaration order rather than alphabetical (agentenv-mail-mcp sits last, after proxy), so where agentenv-pydantic-ai belongs follows wherever the image gets declared.

Each reviewer sees one diff at a time, so none of this shows up on either PR on its own. Offering the comparison, not a verdict on merge order.

---

Generated by Claude Code

[socket-security]

Review the following changes in direct dependencies. Learn more about Socket for GitHub.

Diff	Package	Supply Chain Security	Vulnerability	Quality	Maintenance	License
	pypi/​pydantic-ai-harness@​0.61.0
	pypi/​pydantic-ai-slim@​2.61.0

View full report

[greptile-apps]

Snapshots skip project files

_entry_holding selects the first directory under the workspace, not just the agent's state directory. If the shipped image runs with PYDANTIC_AI_A2A_WORKSPACE=/home, the state lives at /home/agent/.pydantic-ai-a2a, but saving skips all of /home/agent, including project files there. Loading also leaves that whole directory unchanged. Both calls can return success without saving or restoring those files.

Exclude and preserve only the agent's state directory, not its whole ancestor.

Prompt To Fix With AI

This is a comment left during a code review.
Path: src/agent_env/agents/agents/pydantic-ai/pydantic_ai_agent.py
Line: 579

Comment:
**Snapshots skip project files**

`_entry_holding` selects the first directory under the workspace, not just the agent's state directory. If the shipped image runs with `PYDANTIC_AI_A2A_WORKSPACE=/home`, the state lives at `/home/agent/.pydantic-ai-a2a`, but saving skips all of `/home/agent`, including project files there. Loading also leaves that whole directory unchanged. Both calls can return success without saving or restoring those files.

Exclude and preserve only the agent's state directory, not its whole ancestor.

---

For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.