Skip to content

fix(review): prevent empty deep reviews #40

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
luckyPipewrench merged 2 commits into from
Aug 8, 2026
Merged

fix(review): prevent empty deep reviews #40

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a2f60ed
fix(review): prevent empty deep reviews
luckyPipewrench Aug 8, 2026
af2a2c0
test(review): pin corrected deep settings
luckyPipewrench Aug 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions scripts/pr-review.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,11 +47,13 @@
DEFAULT_MODEL_DEEP = "gpt-5.6-terra"
DEFAULT_TEMPERATURE = 0.2
DEFAULT_MAX_COMPLETION_TOKENS = 8192
DEEP_MAX_COMPLETION_TOKENS = 25000
# max_completion_tokens is shared by reasoning and visible output. At xhigh
# effort, 25000 was consumed by reasoning alone and produced an empty review.
DEEP_MAX_COMPLETION_TOKENS = 64000
DEFAULT_LLM_TIMEOUT_SECONDS = 120
DEEP_LLM_TIMEOUT_SECONDS = 300
FAST_REASONING_EFFORT = "low"
DEEP_REASONING_EFFORT = "medium"
DEEP_REASONING_EFFORT = "xhigh"
Comment thread
coderabbitai[bot] marked this conversation as resolved.


class LLMReviewError(RuntimeError):
Expand Down
6 changes: 4 additions & 2 deletions tests/test_pr_review_routing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ def test_model_defaults_and_mode_routing(self):
self.assertEqual(module.model_for_mode("docs"), "gpt-5.6-luna")
self.assertEqual(module.model_for_mode("deep"), "gpt-5.6-terra")
self.assertEqual(module.FAST_REASONING_EFFORT, "low")
self.assertEqual(module.DEEP_REASONING_EFFORT, "medium")
self.assertEqual(module.DEEP_REASONING_EFFORT, "xhigh")

def test_gpt_5_6_payloads_pin_the_requested_reasoning_effort(self):
module = load_pr_review_module()
Expand All @@ -56,13 +56,15 @@ def test_gpt_5_6_payloads_pin_the_requested_reasoning_effort(self):
"system prompt",
"diff",
reasoning_effort=module.DEEP_REASONING_EFFORT,
max_completion_tokens=module.DEEP_MAX_COMPLETION_TOKENS,
)

self.assertEqual(ordinary_payload["model"], "gpt-5.6-luna")
self.assertEqual(ordinary_payload["reasoning_effort"], "low")
self.assertEqual(ordinary_payload["max_completion_tokens"], 8192)
self.assertEqual(deep_payload["model"], "gpt-5.6-terra")
self.assertEqual(deep_payload["reasoning_effort"], "medium")
self.assertEqual(deep_payload["reasoning_effort"], "xhigh")
self.assertEqual(deep_payload["max_completion_tokens"], 64000)

def test_model_repository_variable_overrides(self):
module = load_pr_review_module()
Expand Down
Loading