Repository navigation
Conversation
whatever
approved these changes
Sep 17, 2026
ropoctl
force-pushed
the
fix/sourcehunt-final-synthesis-stall
branch
from
September 18, 2026 20:11
54d9167 to
b4e5155
Compare
ropoctl
changed the base branch from
main
to
fix/sourcehunt-transient-gateway-retry
September 18, 2026 20:11
ropoctl
added this pull request to stack #242
September 18, 2026 20:25
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
A hunt that reaches the late no-progress boundary can enqueue its final-synthesis instruction and then immediately terminate as
stalled. The instruction never reaches the model, so an otherwise bounded investigation cannot produce its intended terminal summary.Fix
Allow a synthesis prompt that was added on the current iteration to reach the model before applying the stall guard. Budget and maximum-step limits still take precedence, and early unproductive loops still terminate normally.
Test plan
uv run --extra dev pytest -q tests/test_sourcehunt*.py tests/test_deep_agent_loop.py— 1123 passeduv run --extra dev ruff check clearwing/sourcehunt/hunter.py tests/test_deep_agent_loop.pyuv run --extra dev ruff format --check clearwing/sourcehunt/hunter.py tests/test_deep_agent_loop.pygit diff --check