Add MseeP.ai badge#2
Open
mseep-ai wants to merge 1 commit into
Open
Conversation
hanlulong
added a commit
that referenced
this pull request
May 30, 2026
Schema bump that unblocks Phase 2.7 (Tier-3 escape hatch) without introducing any behavior change. Adopted Position C from the 3-agent debate over Positions A (add all 5 fields) and B (nest under sub-models): add only the two fields with a scoped downstream consumer; defer yoy_change / rolling_window / aggregation_type until they each have a producer prompt + consumer site landing in the same PR. Adding fields without a scoped consumer recreates the dead-schema problem the deep review explicitly warns against in docs/DEEP_REVIEW_2026-05-30.md §5 Phase 2.6 and §7 anti-pattern #2. Changes: - backend/services/conversation_state_v2.py: FollowUpDelta gains delta_confidence: Optional[float] = None needs_full_rewrite: bool = False with a comment block tying them to Phase 2.7 (Tier-3) and §6 invariant #8 (≥7d shadow-mode before default-on). - backend/services/delta_extractor.py: extended the LLM extraction prompt with (a) four new changed_decomposition few-shot examples for sector / industry / age_group / category / region (T5 critical fix — the user-journey audit found decomposition follow-ups failing silently for non-province breakdowns); (b) STEP 3 — TELEMETRY, instructing the LLM to populate delta_confidence (0.0-1.0) and needs_full_rewrite when the field-by-field delta cannot capture the user's restructuring intent. - backend/tests/test_conversation_state_v2.py: TestPhase26TelemetryFields asserts defaults are inert, round-trips through model_dump, and freezes the merge_state-must-not-consume-these-fields contract. When future PRs wire these fields, those tests are the canary. Verified: 200/200 conversation tests pass. FollowUpDelta now has 25 fields (was 23). No hardcoded semantic rules. Multi-round invariants preserved (delta_confidence + needs_full_rewrite live on FollowUpDelta, not on ConversationState — resolved_indicator_code, statscan_cube_metadata, provider_locked, active_answer_members all untouched). Deep review finding: docs/DEEP_REVIEW_2026-05-30.md Phase 2.6 Co-Authored-By: Claude Opus 4.7 <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.
Hi there,
This pull request shares a security update on openecon-data.
We also have an entry for openecon-data in our directory, MseeP.ai, where we provide regular security and trust updates on your app.
We invite you to add our badge for your MCP server to your README to help your users learn from a third party that provides ongoing validation of openecon-data.
You can easily take control over your listing for free: visit it at https://mseep.ai/app/hanlulong-openecon-data.
Thanks,
The MseeP Team
MCP servers you can trust