feat(evals): publish multimodal_doc parser_compare benchmark + n=171 report

Adds the full parser_compare experiment for the multimodal_doc suite:
six arms compared on 30 PDFs / 171 questions from MMLongBench-Doc with
anthropic/claude-sonnet-4.5 across the board.

Source code:
- core/parsers/{azure_di,llamacloud,pdf_pages}.py: direct parser SDK
  callers (Azure Document Intelligence prebuilt-read/layout, LlamaParse
  parse_page_with_llm/parse_page_with_agent) used by the LC arms,
  bypassing the SurfSense backend so each (basic/premium) extraction
  is a clean A/B independent of backend ETL routing.
- suites/multimodal_doc/parser_compare/{ingest,runner,prompt}.py:
  six-arm benchmark (native_pdf, azure_basic_lc, azure_premium_lc,
  llamacloud_basic_lc, llamacloud_premium_lc, surfsense_agentic) with
  byte-identical prompts per question, deterministic grader, Wilson
  CIs, and the per-page preprocessing tariff cost overlay.

Reproducibility:
- pyproject.toml + uv.lock pin pypdf, azure-ai-documentintelligence,
  llama-cloud-services as new deps.
- .env.example documents the AZURE_DI_* and LLAMA_CLOUD_API_KEY env
  vars now required for parser_compare.
- 12 analysis scripts under scripts/: retry pass with exponential
  backoff, post-retry accuracy merge, McNemar / latency / per-PDF
  stats, context-overflow hypothesis test, etc. Each produces one
  number cited by the blog report.

Citation surface:
- reports/blog/multimodal_doc_parser_compare_n171_report.md: 1219-line
  technical writeup (16 sections) covering headline accuracy, per-format
  accuracy, McNemar pairwise significance, latency / token / per-PDF
  distributions, error analysis, retry experiment, post-retry final
  accuracy, cost amortization model with closed-form derivation, threats
  to validity, and reproducibility appendix.
- data/multimodal_doc/runs/2026-05-14T00-53-19Z/parser_compare/{raw,
  raw_retries,raw_post_retry}.jsonl + run_artifact.json + retry summary
  whitelisted via data/.gitignore as the verifiable numbers source.

Gitignore:
- ignore logs_*.txt + retry_run.log; structured artifacts cover the
  citation surface, debug logs are noise.
- data/.gitignore default-ignores everything, whitelists the n=171 run
  artifacts only (parser manifest left ignored to avoid leaking local
  Windows usernames in absolute paths; manifest is fully regenerable
  via 'ingest multimodal_doc parser_compare').
- reports/.gitignore now whitelists hand-curated reports/blog/.

Also retires the abandoned CRAG Task 3 implementation (download script,
streaming Task 3 ingest, CragTask3Benchmark + tests) and trims the
runner / ingest module APIs to match.

Co-authored-by: Cursor <cursoragent@cursor.com>

surfsense_evals/.env.example

@@ -63,3 +63,21 @@ OPENROUTER_API_KEY=sk-or-...
 # Where generated reports (summary.md / summary.json) get written.
 # Default: <surfsense_evals>/reports/
 # EVAL_REPORTS_DIR=./reports
+
+# ---------------------------------------------------------------------------
+# 5. Parser SDKs — REQUIRED for the multimodal_doc / parser_compare suite
+# ---------------------------------------------------------------------------
+# parser_compare calls Azure Document Intelligence and LlamaParse SDKs
+# directly from the eval harness so each (basic / premium) extraction
+# is a clean A/B test independent of the SurfSense backend's ETL routing.
+#
+# Azure Document Intelligence — used for the `azure_basic_lc` (prebuilt-read)
+# and `azure_premium_lc` (prebuilt-layout) arms. Get an endpoint + key from
+# https://portal.azure.com (Document Intelligence resource, F0 / S0 tier).
+# AZURE_DI_ENDPOINT=https://<your-resource>.cognitiveservices.azure.com/
+# AZURE_DI_KEY=<your-32-char-key>
+#
+# LlamaCloud (LlamaParse) — used for `llamacloud_basic_lc` (parse_page_with_llm)
+# and `llamacloud_premium_lc` (parse_page_with_agent). Get a key from
+# https://cloud.llamaindex.ai/api-key.
+# LLAMA_CLOUD_API_KEY=llx-...