[NOTICKET] anomaly: name the anomalous rows + a flag-rate quality verdict (D-3)

[NOTICKET] data_quality: actually count the duplicate rows it advertises (D-1)

[NOTICKET] docs: PR-0/PR-1 spec for Sofhia, and the feedback-edge before/after

[NOTICKET] chore: untrack a render byproduct, and note what 7ffe004a swept in

[NOTICKET] slow path: don't re-trim a payload the tool already bounded (A30 follow-up)

[NOTICKET] anomaly: bound the returned sample at source, not just the assembler

[NOTICKET] docs: diagram of the agentic path, drawn from the code

[NOTICKET] docs: fill bug 14's commit hash

[NOTICKET] planner: surface numeric min/max, so thresholds aren't chosen blind

[NOTICKET] docs: real commit hashes in the dry-run log

[NOTICKET] assembler: never state the finding a failed step was meant to produce

[NOTICKET] eval(chat_sim): --turns, so verifying a late fix doesn't cost a whole suite

[NOTICKET] planner: exhaustion refuses instead of crashing, + the dry-run findings log

[NOTICKET] fix(planner): three checks for plans that lie about what they selected

[NOTICKET] eval(chat_sim): save a per-run transcript so answers can be audited

[NOTICKET] eval(chat_sim): point the suites at Rifqi's account, unblocking the DB suite

[NOTICKET] eval(chat_sim): four suites, and a refusal when a source isn't registered

[NOTICKET] docs: correct a fabricated commit hash in A30/A31

[NOTICKET] eval(chat_sim): mint a message_id per turn, closing the traceability gap

[NOTICKET] docs: A23 clean run — 6/6 turns, and the four bugs it took to get there

[NOTICKET] fix(planner/slow path): checkable criteria in Indonesian, bound meta too

[NOTICKET] fix(slow path): retry malformed plans, bound stats in the assembler prompt

[NOTICKET] fix(router): route data-condition questions to analysis, not inventory (A23 Bug 4)

[NOTICKET] docs: diagnose the missing data-quality turn — a router miss (A23 Bug 4)

[NOTICKET] docs: record the second A23 dry-run — 5/5 clean, three bugs confirmed

[NOTICKET] fix(planner): surface constant columns, reject constant targets (A23 Bug 3)

[NOTICKET] fix(tools): accept `avg` wherever `mean` works (A23 Bug 2)

[NOTICKET] fix(query): align date filters with date32 columns (A23 Bug 1)

[NOTICKET] eval(chat_sim): retarget at PA Data Dummy for the A23 dry-run

[NOTICKET] planner: group-labelled recipes + the feasibility gate the eval caught (A18)

[NOTICKET] planner: ten exemplars, one per tool that had none (A18, part 1)

[NOTICKET] docs: A18 exemplar spec — the ten questions, agreed before implementation

[NOTICKET] planner: unblock the ML tools A15 just activated (A24, A25)

[NOTICKET] feat(tools): activate all analytical tools (A15)

[NOTICKET] planner: group-first tool selection (A17)

[NOTICKET] fix(tools): analyze_ab_test quality — KeyError on the too-few-rows path

[NOTICKET] tools: quality blocks for forecast + ab_test, forecast backtest, CK7 fix

[NOTICKET] planner: rule 5 forbade the modeling tools we just shipped

[NOTICKET] feat(tools): register analyze_importance + analyze_cluster (DEFERRED) — A8/A10

[NOTICKET] feat(tools): analyze_ab_test — rename analyze_comparison + Welch t-test (A11)

[NOTICKET] feat(tools): analyze_importance + analyze_cluster (unregistered) + CK7

[NOTICKET] docs(knowledge): bring the persistence contract current so it can be sent

[NOTICKET] feat(tools): analyze_segmentation — activate/rename analyze_segment + chart (A13)

[NOTICKET] feat(tools): analyze_data_quality — rename analyze_profile, activate + chart (A14)

[NOTICKET] feat(tools): analyze_pareto — rename analyze_contribution, Pareto 80/20 (A12)

[NOTICKET] feat(report): embed analyze_* auto-charts, share one chart extractor (A21)

[NOTICKET] feat(slow-path): per-step SSE progress, bilingual (A22)

[NOTICKET] docs: mark A7/A9 done + add forecast & anomaly to REPO_STATUS

[NOTICKET] feat(tools): analyze_anomaly (Isolation Forest) — second ML tool, DEFERRED

[NOTICKET] feat(tools): analyze_forecast (ETS) — first ML tool, DEFERRED