From f3705d10c698d913183eb0ef1650dbd25fba10e9 Mon Sep 17 00:00:00 2001
From: Matt <matt@echo6.co>
Date: Sun, 14 Jun 2026 22:59:36 +0000
Subject: [PATCH] Enforce gemini-2.5-flash-lite per Echo6 model policy

Replace gemini-2.0-flash with gemini-2.5-flash-lite across the enrichment
and extraction pipeline (config.yaml, lib/extractor.py) and the six
maintenance scripts. Flash Lite is the mandated model for all Gemini calls.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 config.yaml                    | 2 +-
 lib/extractor.py               | 2 +-
 scripts/cleanup_outliers.py    | 2 +-
 scripts/domain_reenrich.py     | 2 +-
 scripts/migrate_domains.py     | 2 +-
 scripts/migrate_skill_level.py | 2 +-
 scripts/reenrich_reference.py  | 2 +-
 scripts/repair_corrupted.py    | 2 +-
 8 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/config.yaml b/config.yaml
index a2709b0..c3d37da 100644
--- a/config.yaml
+++ b/config.yaml
@@ -40,7 +40,7 @@ vector_db:
   collection: recon_knowledge_hybrid # Collection name
 
 gemini:
-  model: gemini-2.0-flash     # Gemini model for enrichment
+  model: gemini-2.5-flash-lite     # Gemini model for enrichment
   response_mime_type: application/json  # Force JSON output from Gemini
 
 web:
diff --git a/lib/extractor.py b/lib/extractor.py
index bc236ab..b6c0f1c 100644
--- a/lib/extractor.py
+++ b/lib/extractor.py
@@ -197,7 +197,7 @@ def _try_gemini_vision(pdf_path, page_num_1indexed, page_timeout=60):
     for attempt in range(3):
         try:
             genai.configure(api_key=api_key)
-            model = genai.GenerativeModel('gemini-2.0-flash')
+            model = genai.GenerativeModel('gemini-2.5-flash-lite')
             response = model.generate_content([
                 {
                     'mime_type': 'image/png',
diff --git a/scripts/cleanup_outliers.py b/scripts/cleanup_outliers.py
index 694b528..e009ea6 100755
--- a/scripts/cleanup_outliers.py
+++ b/scripts/cleanup_outliers.py
@@ -166,7 +166,7 @@ def classify_concept(title, subdomains, content, key):
     )
     genai.configure(api_key=key)
     model = genai.GenerativeModel(
-        "gemini-2.0-flash",
+        "gemini-2.5-flash-lite",
         generation_config={"response_mime_type": "application/json"}
     )
     for attempt in range(4):
diff --git a/scripts/domain_reenrich.py b/scripts/domain_reenrich.py
index 8a4e57a..d39fa9f 100755
--- a/scripts/domain_reenrich.py
+++ b/scripts/domain_reenrich.py
@@ -98,7 +98,7 @@ def classify_concept(title, subdomains, content, key):
     )
     genai.configure(api_key=key)
     model = genai.GenerativeModel(
-        "gemini-2.0-flash",
+        "gemini-2.5-flash-lite",
         generation_config={"response_mime_type": "application/json"}
     )
     for attempt in range(4):
diff --git a/scripts/migrate_domains.py b/scripts/migrate_domains.py
index 26122ce..ed70a1d 100644
--- a/scripts/migrate_domains.py
+++ b/scripts/migrate_domains.py
@@ -110,7 +110,7 @@ def classify_domain(content, summary, subdomains, key):
     )
     genai.configure(api_key=key)
     model = genai.GenerativeModel(
-        "gemini-2.0-flash",
+        "gemini-2.5-flash-lite",
         generation_config={"response_mime_type": "text/plain"}
     )
 
diff --git a/scripts/migrate_skill_level.py b/scripts/migrate_skill_level.py
index 0c714b2..ac42f27 100755
--- a/scripts/migrate_skill_level.py
+++ b/scripts/migrate_skill_level.py
@@ -117,7 +117,7 @@ def classify(title, domains, subdomains, content, key):
     )
     genai.configure(api_key=key)
     model = genai.GenerativeModel(
-        "gemini-2.0-flash",
+        "gemini-2.5-flash-lite",
         generation_config={"response_mime_type": "application/json"}
     )
     for retry in range(4):
diff --git a/scripts/reenrich_reference.py b/scripts/reenrich_reference.py
index 02b0f18..719033a 100755
--- a/scripts/reenrich_reference.py
+++ b/scripts/reenrich_reference.py
@@ -124,7 +124,7 @@ def classify(title, subdomains, content, key, attempt=0):
     )
     genai.configure(api_key=key)
     model = genai.GenerativeModel(
-        "gemini-2.0-flash",
+        "gemini-2.5-flash-lite",
         generation_config={"response_mime_type": "application/json"}
     )
     for retry in range(4):
diff --git a/scripts/repair_corrupted.py b/scripts/repair_corrupted.py
index 2c83237..792eca1 100755
--- a/scripts/repair_corrupted.py
+++ b/scripts/repair_corrupted.py
@@ -140,7 +140,7 @@ def enrich_window_text(text, key):
     """Call Gemini on raw window text, return concepts list."""
     genai.configure(api_key=key)
     model = genai.GenerativeModel(
-        "gemini-2.0-flash",
+        "gemini-2.5-flash-lite",
         generation_config={"response_mime_type": "application/json"}
     )
     for attempt in range(4):