Conversation
…cination detection Add ToolInvocationPhase enum (Setup/ParamHandling/Execution/ResultInterpretation) mapping all ToolErrorCategory variants to their diagnostic phase per arXiv:2601.16280. Adds error_phase field to AuditEntry for phase-level failure clustering in audit output. Adds tool_provider to OrchestrationConfig for routing tool-heavy tasks to reliable models. Add is_reasoning_model() helper detecting o1/o3/o4, QwQ, DeepSeek-R1, and Claude extended-thinking models per arXiv:2510.22977. AnomalyDetector gains record_reasoning_quality_failure() which counts quality failures from reasoning models in the anomaly window and emits a reasoning_amplification WARN. Adds reasoning_model_warning flag to AnomalyConfig (default: true). Closes #2234, #2284
github-actions
bot
added
documentation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
ToolInvocationPhaseenum (Setup/ParamHandling/Execution/ResultInterpretation) tozeph-tools, mapping allToolErrorCategoryvariants to their diagnostic phase per arXiv:2601.16280error_phase: Option<String>toAuditEntryfor phase-level failure clustering in[tools.audit]outputtool_providerfield toOrchestrationConfigfor routing tool-heavy tasks to reliability-optimized models (prefer qwen2.5:14b-equivalent)is_reasoning_model()helper detecting o1/o3/o4-mini, QwQ, DeepSeek-R1, and Claude extended-thinking model families per arXiv:2510.22977AnomalyDetector::record_reasoning_quality_failure()— records quality failures from reasoning models in the anomaly window and emits areasoning_amplificationWARNreasoning_model_warning: boolflag toAnomalyConfig(default:true)Closes #2234, #2284
Test plan
cargo nextest run --workspace --features full --lib --bins— 7049/7049 passcargo clippy --workspace --features full -- -D warnings— cleancargo +nightly fmt --check— clean