OpenRouter agent

[shfunc]

• Adds OpenRouterAgent (Responses API): message/role mapping, tool-call conversion, prompt caching, schema sanitization, and image handling (testing).
• Basic tests pass; included a tiny OpenRouter quickstart example (inline task).
• Differences across agents: OpenAI-compatible uses Chat Completions; OpenRouter uses Responses adapter; both share the same MCPAgent interface.

Can be tested with these commands:

python examples/04_openrouter_quickstart.py

hud eval hud-evals/SheetBench-50 openrouter --model z-ai/glm-4.5v -v

---

Note

Introduces an OpenRouter-based agent (GLM-4.5V, UITARS) with shared computer-use helpers, tests, and full CLI/eval/factory integration.

• Agents:
  • Add OpenRouterBaseAgent and OpenRouterAgent dispatcher with adapter registry/loader.
  • Implement adapters: Glm45vAgent (hud/agents/openrouter/models/glm45v) and UITarsAgent (hud/agents/openrouter/models/uitars) with prompt construction, response parsing, action conversion, and image handling; include action_space.txt.
  • Shared helpers in hud/agents/openrouter.py for reasoning/output items, computer-use actions, coordinate coercion, JSON action parsing, image extraction, and tool result rendering.
  • Export OpenRouterAgent in hud/agents/__init__.py.
• CLI/Eval:
  • Add openrouter agent option and help text in hud/cli/__init__.py; include in valid choices and interactive selection.
  • Update hud/cli/eval.py to support openrouter in types/flows, normalize model, resolve adapter, and construct agent; wire API key via LiteLLM/OpenRouter.
• Utils:
  • Add create_openrouter_agent factory in hud/utils/agent_factories.py.
• Tests:
  • Add hud/agents/tests/test_openrouter.py covering default model selection, alias normalization, error on unknown model, message→tool-call parsing, and tool result formatting.

^{Written by Cursor Bugbot for commit 1279555. This will update automatically on new commits. Configure here.}

[promptless]

📝 Documentation updates detected!

Updated existing suggestion: Add and update OpenRouter agent documentation for PR #163 and PR #166

[shfunc]

• added the glm-4.5v computer-use adapter (prompt glue + action parser) and updated the
  openrouter wrapper to dispatch to it
• adjusted the openrouter unit test to mock litellm, check the decoded openai_computer tool
  call, and cover tool-result formatting
• bumped the agent dependency to litellm

Have a couple of questions: Do we want to keep model-specific adapters in separate top-level modules
(like the new glm45v.py), or should we group them under an openrouter/ subpackage so adding
more models stays organized?