fix(llm): correct ContextManagement serialization for Claude server compaction API#1709
Merged
fix(llm): correct ContextManagement serialization for Claude server compaction API#1709
Conversation
…ompaction API
The ContextManagement struct was serializing as:
{ "type": "enabled", "trigger_tokens": 50000 }
The Claude API expects:
{ "type": "auto_truncate", "trigger": { "type": "input_tokens", "value": 50000 }, "pause_after_compaction": false }
This mismatch caused a 400 Bad Request on every request with
--server-compaction enabled, making the feature completely non-functional.
Restructure ContextManagement into two structs (ContextManagement +
ContextManagementTrigger) with correct field names and values.
Update tests to assert the correct JSON shape.
Closes #1705
This was referenced Mar 13, 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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
--server-compactionflag which caused a400 Bad Requeston every request withcontext_management.type: Extra inputs are not permittedContextManagementnow serializes to the correct Claude API format:{ "type": "auto_truncate", "trigger": { "type": "input_tokens", "value": N }, "pause_after_compaction": false }ContextManagementTypeenum with two plain structs (ContextManagement+ContextManagementTrigger) using&'static strfor type discriminantsRoot Cause
PR #1696 introduced the
ContextManagementstruct with wrong field names:type: "enabled"→ should be"auto_truncate"trigger_tokens: u32(flat) → should be nestedtrigger: { type: "input_tokens", value: N }Test plan
context_management_*unit tests pass with the correct JSON assertionscargo +nightly fmt --checkcleancargo clippy --workspace --features full -- -D warningscleanCloses #1705