Release v1.3.1#47
Merged
Merged
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
[v1.3.1] — 2026-03-28
Added
eval/,src/post_sim_artifacts.py): introduced 11 new evaluation question types including ZD_RESOLUTION, SF_RISK, and INVOICE_SLA. The framework now includes specialized scorers for financial credits, NPS drivers, and PR review verdicts to validate RAG performance across the entire business logic stack.src/external_email_ingest.py): implemented a probabilistic customer response system. The simulation now classifies inbound emails (Complaints vs. Feature Requests) and allows customers to autonomously advance Salesforce Opportunity stages based on the quality of outbound sales replies.src/embed_worker.py): replaced the serial background worker with aThreadPoolExecutor-based system. This supports high-throughput embedding via Infinity (up to 16 concurrent calls) while maintaining causal consistency through a newdrain()synchronization mechanism.eval/eval_e2e.py): added support for Reciprocal Rank Fusion (RRF) and Graph-Augmented Retrievers, allowing the evaluation agent to fuse BM25 lexical search with dense vector embeddings and 2-hop artifact expansion.Changed
src/utils/persona_utils.py): refactored persona generation into a centralizedPersonaUtilssingleton. Voice cards now inject "CRM Pressure" hints, causing internal employees to exhibit higher stress and terser communication when they own at-risk deals or urgent Zendesk tickets.src/graph_dynamics.py,src/flow.py): integrated live Salesforce/Zendesk telemetry into the social graph. Edge weights between liaisons and external contacts now fluctuate based on account sentiment, and stress propagates through the organization when "lighthouse" customers flag risks.src/flow.py): updated the incident generator to be reactive to the daily planning theme. Stability "collisions" are now more likely to fire if the daily plan involves high-risk activities like "migrations" or "refactors" identified via keyword triggers.src/memory.py): migrated therecall_with_rewritelogic from a generic callable to a native Bedrock-hosted Llama 3.3 implementation for more robust hypothetical document generation.Fixed
src/normal_day.py): fixed a bug where engineers would requested changes indefinitely by implementing "Review Round" guidance, forcing approvals after 3 rounds unless critical bugs are present.src/external_email_ingest.py): corrected an issue where inbound vendor emails were orphaned; all external communications are now properly rooted in aCausalChainHandlerand tracked through downstream JIRA/Slack artifacts.src/email_gen.pyscript in favor of the live, event-driven ingestor system.