fix: retry when LLM returns text instead of calling final_response#3850
Merged
fix: retry when LLM returns text instead of calling final_response#3850
Conversation
Instead of raising RuntimeError immediately when the LLM returns a text response instead of calling the `final_response` tool for structured output, retry up to 3 times with an explicit nudge message asking the model to use the tool. This mirrors the existing retry behavior for validation errors but with a separate, smaller cap. Fixes #3847 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
marvin-context-protocol
Bot
added
bug
strawgate
changed the title
Tests cover: - Text response followed by successful final_response (retry works) - Text response exceeding max retries (raises RuntimeError) - Nudge message appended to history on retry - No retry when result_type is None (text is valid) Addresses review feedback from PR review tool (v1 flagged missing tests as high severity). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
strawgate
changed the title
Remove test_nudge_message_in_history (implementation detail). Reduce boilerplate in remaining 3 tests. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
Contributor
Test Failure AnalysisSummary: The Root Cause: In Suggested Solution: Run # Before (current)
ToolUseContent(
type="tool_use", id="c1", name="final_response", input={"value": value}
)
# After (ruff-formatted)
ToolUseContent(
type="tool_use",
id="c1",
name="final_response",
input={"value": value},
)Detailed AnalysisFailed hook: Workflow run: #24292594795, job Relevant log excerpt: Related Files
|
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
strawgate
removed
the
DON'T MERGE
strawgate
added a commit
to strawgate/fastmcp
that referenced
this pull request
Apr 12, 2026
The merge of PrefectHQ#3850 and PrefectHQ#3851 dropped the variable initialization. text_response_retries was used at line 707 but never assigned. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
jlowin
approved these changes
Apr 12, 2026
Member
jlowin
left a comment
jlowin
left a comment
There was a problem hiding this comment.
Mirrors the existing validation-retry convention and handles the real UX cliff where some models ignore tool_choice=required. Bounded at 3 retries.
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.
Fixes #3847
Problem
sample_implat line 685 raisesRuntimeErrorimmediately when structured output is expected but the LLM returns text instead of callingfinal_response. No retry, no nudge — just a crash.This contrasts with validation errors (lines 657-679) which append feedback to history and retry. Some models occasionally ignore
tool_choice="required"and return text, especially on later iterations of the tool loop after gathering information.Fix
Add a retry loop (capped at 3 attempts) that appends a nudge message asking the model to use the
final_responsetool, matching the existing pattern for validation error retries.After exhausting retries, raises
RuntimeErrorwith the attempt count.Tests
3 tests: retry-then-succeed, exceed-max-retries, and no-retry-when-result_type-is-None.
🤖 Generated with Claude Code