Feature/hypertension rag#1
Merged
Merged
Conversation
- Task 7: appraise_agent.py GRADE scoring with SR/MA/NMA included_study_type,
upgrade blocking on serious bias, confounding_bias_mitigates
- Task 8: appraise_agent.txt prompt updated with included_study_type,
confounding_bias_mitigates, upgrade_blocked_by_bias fields
- Task 9: apply_agent.py route_type injection, structured GRADE summary,
inconsistency enforcement
- Task 10: apply_agent.txt updated with {route_type} input
- Task 11-14: judge prompts rewritten with Gate+Rubrics architecture
- Task 15: assess_judge.txt updated with route_type/route_confidence/
ebm_query inputs, route_confidence_noted output
- Task 16: judge_llm.py Gate+Rubrics scoring, RUBRIC_WEIGHTS,
_check_gates, _score_rubrics
- Task 17: tests/test_judge_rubrics.py (6 tests),
tests/test_integration_routing.py (4 tests)
- Task 18: 15/15 tests passing
…ctor Snapshot of the current operating mode prior to refactoring evidence acquisition to the hypertensiondb RAG service. - Modified agents, prompts, coordinator, judge: all reflect the 4/20-4/22 redesign output that has been the working system since. - Deleted obsolete plans/specs from 2026-03~04. - Added router_unified.txt (V2 unified Ask router) and tests/agents/ package which were never committed but are functionally part of the running system. - hypertension/ added to .gitignore (separate sibling repo, not a submodule). Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
- Acquire agent now queries hypertension_rag_client (HTTP) instead of PubMed + MedCPT; removes pubmed_api.py and local_evidence_db.py - Add src/tools/hypertension_rag_client.py: retrying HTTP client that aggregates chunk-level results into paper-level Evidence objects - Update state schema: Evidence gains supporting_passages field - Update all agent prompts and judge rubrics for RAG-sourced evidence - Merge Ask router into single LLM call (router_unified.txt) - Add concurrent LLM warm-up at startup to cut cold-start latency - Fix requirements.txt: replace langchain/torch/chromadb stack with openai + httpx; update README to reflect new architecture
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
Related Issue
Closes #
How to Test
Checklist
make lintpassesmake testpasses (or no tests affected).env.exampleupdated if new env vars added