marek/creator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
team3
2026-07-06 14:44:20 +02:00
parent f4c5116abb
commit cc27e53b9e
20 changed files with 504 additions and 267 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
backend/config.py
View File

@@ -135,21 +135,6 @@ CONSENSUS_GRACE = 300
# check loops leave any remaining objections standing after that.
CONSENSUS_MAX_ROUNDS = 3
# Crawler triage (content/noise) — deterministic rule filter instead of an LLM.
# Match: substring (lowercase) against URL AND file name. Order: keep > noise > min_chars > keep.
# Just add special rules here.
CRAWL_KEEP_PATTERNS = ["learn-unit", "learn-course"] # always content
CRAWL_NOISE_PATTERNS = [ # clearly off-topic → out
"clubs", "events", "podcasts", "resources", "-u-",
"academy", "pricing", "/plans", "career", "newsletter", "impressum", "login",
]
CRAWL_MIN_CHARS = 400 # too little text → out
# LLM topic relevance gate (after the rule filter): per content page yes/no against the spec.
# Separates the subject area (e.g. backend vs frontend), which the global CRAWL_* rules can't.
QUELLE_RELEVANZ_CHUNK = 12 # pages per rater package (small, since a snippet ships per page)
QUELLE_RELEVANZ_SNIPPET = 800 # body characters per page in the prompt (URL is the primary signal)
# QA gate: after the inventory phase an automatic QA run scores the blocks; below the
# threshold the flow PAUSES before board 2 burns tokens (frontend offers force-continue).
QA_GATE_NOTE = 9.5 # 0 = gate off; quota-based, so the tolerated finding count scales with topic size