deploy: sys.path bootstrap so HF doesn't need pip-installed package

deploy: fix HF pip path (-e . → -e /app)

deploy: Space-friendly README with HF frontmatter

chore(gitignore): catch all *.env files

deploy: HF Spaces config for the Streamlit demo (#2)

Merge pull request #1 from laharikarumanchi-AI-ML/docs/add-readme

docs: add README

ci: add GitHub Actions pytest workflow + PR template

Update portfolio plan: Astro v6 content-config shape

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

Add implementation plan for the portfolio website

test(eval): cover loader (join + subset + skip) and scorer integration

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

feat(demo): Streamlit UI with pre-vetted datasets

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

test(orchestrator): retry-off ablation mode fails on first error

test(orchestrator): cover format_observation and dataset_preview

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

feat(prompts): system prompt with @name [value] answer format

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

Fix Task 11 prompt: don't tell LLM to use Agg backend

test(sandbox): verify kernel state persists across cells

test(sandbox): verify matplotlib figures are captured as PNG

test(sandbox): verify timeout interrupts long-running cells

test(sandbox): cover exception traceback capture

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

chore: scaffold Python package and dev environment

Patch plan for Phase 0 discoveries

docs(spec): record Phase 0 scorer-integration decision (A2)

chore: gitignore external/ and eval results

Close two minor gaps from re-review

Revise DA agent plan per reviewer findings

Add implementation plan for the data analysis agent

Address spec-review findings on both designs

Add design specs for data-analysis agent and portfolio site