woogi
d37ac8c1c7
- ENABLE_CODE_REVIEW flag (default off): skips code/ADA/jurisdiction review path in both pipelines; nothing deleted, one env flag to restore. - Per-sheet Drawing Integrity QA wave (agent + classic, default on): dangling refs, on-sheet contradictions, dimension sanity, missing sheet essentials, tag hygiene. New DrawingIntegrityAgent + classic stage. - Broadened conflict critic: intra-sheet + same-discipline contradictions, not just cross-discipline. - Wave 6.5 Brain-directed clarification (bounded hub-and-spoke): Brain names uncertain findings, verify_evidence requests route through the wave-5b verifier; refuted findings suppressed. One planning call + capped verifies, single iteration. Shared _build_verify_scopes across 5b and 6.5. - Config knobs, .env.example, frontend copy, tests (182 passing).
121 lines
4.5 KiB
Bash
121 lines
4.5 KiB
Bash
# Copy to backend/.env and fill in your OpenRouter key.
|
|
|
|
AI_BASE_URL=https://openrouter.ai/api/v1
|
|
AI_API_KEY=sk-or-...
|
|
MODEL=google/gemini-2.5-pro
|
|
|
|
# Optional Agent-mode OpenRouter model overrides (inherit MODEL/TEXT_MODEL when blank)
|
|
AGENT_EXTRACT_MODEL=
|
|
AGENT_INDEX_MODEL=
|
|
AGENT_JURISDICTION_MODEL=
|
|
AGENT_LINKER_MODEL=
|
|
AGENT_CONFLICT_MODEL=
|
|
AGENT_CODE_MODEL=
|
|
AGENT_CONSTRUCT_MODEL=
|
|
AGENT_COMPLETENESS_MODEL=
|
|
AGENT_BRAIN_MODEL=
|
|
AGENT_RFI_MODEL=
|
|
|
|
# Agent-mode hard scope limits / concurrency
|
|
AGENT_LINK_MAX_ASSERTIONS=60
|
|
AGENT_CLUSTER_MAX_ASSERTIONS=24
|
|
AGENT_CONFLICT_MAX_IMAGES=6
|
|
AGENT_CODE_BATCH_SIZE=60
|
|
AGENT_BRAIN_MAX_TOKENS=16384
|
|
AGENT_LINK_CONCURRENCY=4
|
|
AGENT_CONFLICT_CONCURRENCY=4
|
|
AGENT_SPECIALIST_CONCURRENCY=4
|
|
AGENT_RFI_CONCURRENCY=4
|
|
|
|
# -- Review focus toggles -------------------------------------------
|
|
# ENABLE_CODE_REVIEW: run the code/ADA/jurisdiction review path (both pipelines).
|
|
# Default OFF - the product focuses on drawing integrity and cross-discipline
|
|
# coordination, not code/accessibility compliance. Set to 1 to restore it.
|
|
ENABLE_CODE_REVIEW=false
|
|
# ENABLE_DRAWING_INTEGRITY: per-sheet Drawing Integrity QA wave (both pipelines).
|
|
# The drawing-focused pass - dangling references, on-sheet contradictions,
|
|
# dimension sanity, missing sheet essentials, tag hygiene. Default ON.
|
|
ENABLE_DRAWING_INTEGRITY=true
|
|
AGENT_INTEGRITY_MODEL=
|
|
AGENT_INTEGRITY_CONCURRENCY=4
|
|
AGENT_INTEGRITY_MAX_IMAGES=1
|
|
AGENT_INTEGRITY_MAX_ASSERTIONS=80
|
|
INTEGRITY_MAX_TOKENS=16384
|
|
# Skip sheets with fewer than this many extracted objects (too sparse to check)
|
|
INTEGRITY_MIN_ASSERTIONS=3
|
|
|
|
# Agent-mode human-review gate (pipeline stops after Brain until a human reviews)
|
|
AGENT_REQUIRE_REVIEW=true
|
|
# Max clean clusters added to the review queue as non-blocking spot-checks
|
|
AGENT_REVIEW_AUDIT_SAMPLE=5
|
|
# Allow future cross-job review-feedback aggregation to include source_text/images/comments
|
|
REVIEW_AGGREGATE_INCLUDE_TEXT=false
|
|
|
|
# Pipeline tuning
|
|
PDF_DPI=100
|
|
MAX_PAGES=60
|
|
MAX_DIMENSION=2400
|
|
LLM_TIMEOUT=180
|
|
EXTRACT_MAX_TOKENS=65536
|
|
# Reasoning effort for per-sheet extraction (low keeps Gemini thinking tokens
|
|
# from eating the output budget). Blank = don't send the parameter.
|
|
EXTRACT_REASONING_EFFORT=low
|
|
# Hard thinking-token budget for extraction (OpenRouter reasoning max_tokens /
|
|
# Gemini thinking_budget). Stronger than effort; 0 = fall back to effort only.
|
|
EXTRACT_REASONING_MAX_TOKENS=2048
|
|
REASON_MAX_TOKENS=4096
|
|
EXTRACT_CONCURRENCY=4
|
|
REASON_CONCURRENCY=4
|
|
|
|
# Public URL users reach this server on (used for the link in result emails)
|
|
APP_BASE_URL=https://conchecker.scoutitsystems.com
|
|
# APP_BUILD is set by CI at image build time (sha-<short_sha>) - do not set manually.
|
|
|
|
# LLM observability (job-log verbosity + raw request/response dumps)
|
|
# LLM_VERBOSE: one line per LLM call in job.log (model, sizes, item counts, cost)
|
|
# LLM_RAW_DUMP: full prompt+response per call in outputs/<job_id>/llm_raw/
|
|
# (base64 images excluded). Both default on; set false to quiet down.
|
|
LLM_VERBOSE=true
|
|
LLM_RAW_DUMP=true
|
|
|
|
# Email notifications (optional). Leave SMTP_HOST blank to disable.
|
|
# Examples:
|
|
# Gmail: SMTP_HOST=smtp.gmail.com SMTP_PORT=587 (use an App Password)
|
|
# M365: SMTP_HOST=smtp.office365.com SMTP_PORT=587
|
|
SMTP_HOST=
|
|
SMTP_PORT=587
|
|
SMTP_USER=
|
|
SMTP_PASSWORD=
|
|
SMTP_FROM=
|
|
SMTP_USE_TLS=true
|
|
SMTP_USE_SSL=false
|
|
|
|
# Wave 5b evidence verification (vision fact-check of cited sheet text)
|
|
AGENT_VERIFY_MAX_CHECKS=20
|
|
AGENT_VERIFY_SEVERITIES=critical,high
|
|
AGENT_VERIFY_REASONING_EFFORT=low
|
|
VERIFY_MAX_TOKENS=8192
|
|
|
|
# Wave 6.5 Brain-directed clarification (bounded hub-and-spoke). After the Brain
|
|
# merge, the Brain names findings it is unsure about; verify_evidence requests
|
|
# route back through the wave-5b verifier. One planning call + at most
|
|
# BRAIN_CLARIFY_MAX_REQUESTS verifications, single iteration. Default ON.
|
|
ENABLE_BRAIN_CLARIFY=true
|
|
BRAIN_CLARIFY_MAX_REQUESTS=8
|
|
BRAIN_CLARIFY_MAX_TOKENS=4096
|
|
|
|
# Text-layer grounding (deterministic PDF text layer via PyMuPDF)
|
|
# TEXT_LAYER_ENABLED: master switch for text-layer extraction/grounding
|
|
# TEXT_LAYER_MIN_CHARS: below this per page the sheet stays vision-only
|
|
# TEXT_LAYER_MAX_CHARS: cap of text layer injected into the extractor prompt
|
|
# VERIFY_TEXT_MAX_CHARS: cap of the text-layer excerpt in verify scopes
|
|
# VERIFY_HI_DPI_CROPS: evidence-located high-DPI crops in the verifier
|
|
# VERIFY_CROP_DPI / VERIFY_CROP_MARGIN_PTS: crop render DPI / padding (PDF points)
|
|
TEXT_LAYER_ENABLED=true
|
|
TEXT_LAYER_MIN_CHARS=20
|
|
TEXT_LAYER_MAX_CHARS=12000
|
|
VERIFY_TEXT_MAX_CHARS=8000
|
|
VERIFY_HI_DPI_CROPS=true
|
|
VERIFY_CROP_DPI=300
|
|
VERIFY_CROP_MARGIN_PTS=36
|