From 499074b564dc75ae6185c6f14b4df3f4037d4562 Mon Sep 17 00:00:00 2001 From: Matt Van Horn <455140+mvanhorn@users.noreply.github.com> Date: Mon, 23 Mar 2026 17:28:01 -0700 Subject: [PATCH] fix(youtube): pass full transcripts to LLM instead of truncating to 200 chars TRANSCRIPT_MAX_WORDS raised from 500 to 5000 so the LLM gets the full content of most videos (up to ~25 minutes). Removed the second 200-char truncation in render.py that was reducing transcripts to a single sentence before the judge agent ever saw them. Co-Authored-By: Claude Opus 4.6 --- scripts/lib/render.py | 5 +---- scripts/lib/youtube_yt.py | 2 +- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/scripts/lib/render.py b/scripts/lib/render.py index 5944c3a..19bd7fc 100644 --- a/scripts/lib/render.py +++ b/scripts/lib/render.py @@ -258,10 +258,7 @@ def render_compact(report: schema.Report, limit: int = 15, missing_keys: str = " lines.append(f" {item.title}") lines.append(f" {item.url}") if item.transcript_snippet: - snippet = item.transcript_snippet[:200] - if len(item.transcript_snippet) > 200: - snippet += "..." - lines.append(f" Transcript: {snippet}") + lines.append(f" Transcript: {item.transcript_snippet}") lines.append(f" *{item.why_relevant}*") lines.append("") diff --git a/scripts/lib/youtube_yt.py b/scripts/lib/youtube_yt.py index a0fe840..b7ac513 100644 --- a/scripts/lib/youtube_yt.py +++ b/scripts/lib/youtube_yt.py @@ -33,7 +33,7 @@ TRANSCRIPT_LIMITS = { } # Max words to keep from each transcript -TRANSCRIPT_MAX_WORDS = 500 +TRANSCRIPT_MAX_WORDS = 5000 from .relevance import token_overlap_relevance as _compute_relevance