From 017656d97b19d6d79bdb27a00d079b021da15505 Mon Sep 17 00:00:00 2001
From: asepharyana <superaseph@gmail.com>
Date: Thu, 20 Aug 2026 11:30:10 +0700
Subject: [PATCH] feat: update models to
 claude-opus-5/sonnet-5/haiku-4-5-20251001 (tested live on 9router)

- PRIMARY: openai/claude-opus-5 (was openai/claude-opus-4-8)
- FALLBACKS: added openai/claude-sonnet-5, openai/claude-haiku-4-5-20251001
- Verified all three return valid responses via raw HTTP to 9router
- Updated run_server.py, health-check.py, setup_all.py
---
 health-check.py | 4 ++--
 run_server.py   | 6 +++---
 setup_all.py    | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/health-check.py b/health-check.py
index ce92780..62fdbc1 100644
--- a/health-check.py
+++ b/health-check.py
@@ -19,8 +19,8 @@ from pathlib import Path
 
 BWS_SECRET_ID = "2aef2194-971d-4dae-99dd-b49a0041f97c"
 ROUTER_BASE = "https://9router.asepharyana.my.id/v1"
-PRIMARY = "openai/claude-opus-4-8"
-FALLBACKS = ["openai/ATLAS", "openai/gemini", "openai/text", "openai/deepseek-v4-flash-free"]
+PRIMARY = "openai/claude-opus-5"
+FALLBACKS = ["openai/claude-sonnet-5", "openai/claude-haiku-4-5-20251001", "openai/ATLAS", "openai/gemini", "openai/text", "openai/deepseek-v4-flash-free"]
 # Caddy 9router route is now response_header_timeout 120s / read 300s.
 # LLM combo TTFT often 30-40s+. Give the check room to complete.
 HTTP_TIMEOUT = 150
diff --git a/run_server.py b/run_server.py
index a5be52b..7baa811 100644
--- a/run_server.py
+++ b/run_server.py
@@ -26,10 +26,10 @@ os.environ["OPENAI__API_BASE"] = os.environ.get(
     "OPENAI_API_BASE", "https://omniroute.imrnes.team/v1"
 )
 os.environ["OPENAI__KEY"] = omni_key
-os.environ["CONFIG__MODEL"] = os.environ.get("PR_AGENT_MODEL", "openai/claude-opus-4-8")
+os.environ["CONFIG__MODEL"] = os.environ.get("PR_AGENT_MODEL", "openai/claude-opus-5")
 os.environ["CONFIG__FALLBACK_MODELS"] = os.environ.get(
     "PR_AGENT_FALLBACK_MODELS",
-    '["openai/ATLAS","openai/gemini","openai/text","openai/deepseek-v4-flash-free"]',
+    '["openai/claude-sonnet-5","openai/claude-haiku-4-5-20251001","openai/ATLAS","openai/gemini","openai/text","openai/deepseek-v4-flash-free"]',
 )
 os.environ["CONFIG__CUSTOM_MODEL_MAX_TOKENS"] = os.environ.get(
     "PR_AGENT_MAX_TOKENS", "128000"
@@ -261,7 +261,7 @@ if __name__ == "__main__":
     port = int(os.environ.get("PORT", "3000"))
     print(f"PR-Agent GitHub App server starting...")
     print(f"  App ID: {os.environ.get('GITHUB_APP_ID', '')}")
-    print(f"  Model: {os.environ.get('PR_AGENT_MODEL', 'openai/claude-opus-4-8')} via omniroute")
+    print(f"  Model: {os.environ.get('PR_AGENT_MODEL', 'openai/claude-opus-5')} via omniroute")
     print(f"  Endpoint: /api/v1/github_webhooks")
     print(f"  Analytics: {ANALYTICS_DIR}")
     print(f"  Port: {port}")
diff --git a/setup_all.py b/setup_all.py
index f2f32c3..72298c9 100644
--- a/setup_all.py
+++ b/setup_all.py
@@ -78,8 +78,8 @@ with open(BASE_DIR / ".secrets.toml", "w") as f:
 
 # ── 4. Create PR-Agent config ──
 config_toml = """[config]
-model = "openai/claude-opus-4-8"
-fallback_models = ["openai/ATLAS", "openai/gemini", "openai/text", "openai/deepseek-v4-free"]
+model = "openai/claude-opus-5"
+fallback_models = ["openai/claude-sonnet-5", "openai/claude-haiku-4-5-20251001", "openai/ATLAS", "openai/gemini", "openai/text", "openai/deepseek-v4-flash-free"]
 custom_model_max_tokens = 128000
 git_provider = "github"
 publish_output = true