Multi-hop promotion fix + CONTRIBUTING + aspirational ROADMAP - #6
Merged
Conversation
Centralize promotion inlining in Session.self_contained_sql_for_turn(): include prior-turn and within-turn hop synthetics but exclude the answer's own turn alias (which shadowed CTE names when promoting). Agent build action and dashboard promotion both use it; build now errors cleanly when the last answer has no SQL. Adds conversation/ multi-hop test coverage (tests/test_conversation.py). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
CONTRIBUTING encodes the working rules: deterministic core / AI at the edges as a hard boundary, attack-first tests for guard changes, the offline test + lint gate, and the solo-practitioner scope filter. ROADMAP maps v0.3 (accumulation layer: grain tests, metric registry, templates) through doctor/sentinel/MCP directions to the one-person data platform north star. README links both. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What's in here
Fix (was sitting uncommitted):
Session.self_contained_sql_for_turn()centralizes the inlining used when promoting a chat answer to a dbt model — includes prior-turn and within-turn hop synthetics but excludes the answer's own turn alias, which previously shadowed CTE names. Agent build action and dashboard promotion both use it; build errors cleanly when the last answer has no SQL. New conversation/multi-hop test coverage.CONTRIBUTING.md (new): deterministic-core/AI-at-the-edges as a hard boundary, attack-first tests for read-only-guard changes, the offline test + lint gate, solo-practitioner scope filter.
ROADMAP.md (new): explicitly aspirational — v0.3 accumulation layer (grain tests, metric registry, spec/decision templates, all explained in plain English) →
sediment doctor→ sentinel mode → shareable Ask + MCP server → the layered-stack v1.0 → the one-person data platform north star. README links both docs.Verification
ruff check .cleanpytest -m "not live"— 114 passed (includes the new tests/test_conversation.py)🤖 Generated with Claude Code