Gemini: scrub key from URL + throttle between calls

Add GeminiClient — needed for the real benchmark run

Fix Groq rate-limit handling — discovered during real eval run

feat(eval): DABench harness with official scorer (Path A2)

feat(cli): python -m agent ask --data X 'Q'

feat(orchestrator): agent loop with sandbox execution and trace

feat(orchestrator): parse <code>/<answer> blocks from LLM output

feat(trace): JSON trace log of agent steps

feat(llm_client): exponential-backoff retry on 429/5xx

feat(llm_client): add Groq client with mocked-HTTP tests

feat(sandbox): execute code in a Jupyter kernel and capture stdout

chore: scaffold Python package and dev environment