fix: return synthetic empty text on Anthropic empty content response#171
Merged
jamiepine merged 2 commits intospacedriveapp:mainfrom Feb 23, 2026
Merged
Conversation
Marenz
force-pushed
the
fix/anthropic-empty-response
branch
from
85f1ac9 to
64a0ecf
Compare
Anthropic returns an empty content array (stop_reason=end_turn) after side-effect-only tool calls like react or skip — the model has nothing further to say but the response is valid. Previously this was treated as an error, exhausting retries and falling through to the next model in the fallback chain, which then failed for unrelated reasons (e.g. deepseek-reasoner expecting reasoning_content). Return a synthetic empty Text response instead so the agentic loop terminates gracefully.
Marenz
force-pushed
the
fix/anthropic-empty-response
branch
from
64a0ecf to
8ddf516
Compare
jamiepine
approved these changes
Feb 23, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Anthropic returns an empty content array (
stop_reason=end_turn) after side-effect-only tool calls likereactorskip— the model has nothing further to say but the response is otherwise valid.Previously this was treated as a
CompletionError, which exhausted retries and fell through to the next model in the fallback chain. That model then failed for unrelated reasons (e.g. deepseek-reasoner expectingreasoning_contentin history).Return a synthetic
Text { text: "" }response instead so the agentic loop terminates gracefully with no wasted retries or spurious fallbacks.Depends on #174.