Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "collapsed_as_built"
⟨64 unchanged words⟩ duration of every ``affected_activity`` is shortened by ``impact_days`` working days on that activity's calendar (orremoved entirely if``removal_method="remove"``), then CPMre-runs and theresulting "but-for" finish date is comparedto the as-builtfinish. Cumulative pass removes ALL events atonce for aproject-level but-for finish. Every finish shift is stated in working days on ``workday_calendar``; the calendar-day span of the same shift is kept beside it, and ``day_unit_basis`` names the unit of every bare ``*_days`` key in the result. Use this tool when opposing counsel demands a ⟨59 unchanged words⟩ (list of task_codes), and ``impact_days`` (number of working days on the affected activity's calendar). Optional: ``removal_method`` ('shorten'|'remove'), ``responsible_party``, ⟨37 unchanged words⟩ ", "per_event_results": [{event_id, but_for_finish,impact_days_collapsedimpact_workdays_collapsed, collapse_state, duration_removal_basis, finish_driver_after_removal, ...}, ...], # impact_workdays_collapsed is the event's finish shift in # working days on workday_calendar. Each event also carries # impact_days_collapsed: the same shift in calendar days. # duration_removal_basis discloses WHAT duration was removed # and ⟨35 unchanged words⟩ data dates. "cumulative_but_for_finish": "YYYY-MM-DD", "cumulative_impact_workdays": int, # working days on workday_calendar "cumulative_impact_days": int, # the same shift in calendar days "cumulative_collapse_state": str, # a 'locked_by_actuals' zero is not "no impact" "workday_calendar": str, # the calendar every working-day figure is stated on "day_unit_basis": dict, # each bare *_days key: 'working_days' or 'calendar_days' "dual_method_gap": dict | None, # working days only "output_files": {...}, "warnings": ⟨7 unchanged words⟩
Changed the definition of "forensic_windows_analysis"
⟨39 unchanged words⟩ shifts, per-window slip registers (per-activity slip withcritical/non-criticala critical flag (total float of zero or less, or the driving path in a schedule with negative float)), per-window durationgrowth oncritical-path activities, per-window per-party attribution (Owner / ⟨287 unchanged words⟩ clean files); each is also a data-quality warning "analysis"."criticality_basis": the schedules read by their driving path because they have negative float, and those beside them ([] when no schedule has negative float); the box they write is one data-quality warning } On failure: {"error": "
Changed the definition of "concurrent_delay_matrix", "forensic_windows_analysis" and "slip_velocity"
⟨486 unchanged words⟩ 29R-03 §3.3.I (apportionment) · §4.2 (concurrency)", "data_date_corrections": the record of each update whose data date was moved to its latest actual, and of a baseline with actual dates after its data date ([] on clean files); each is also a data-quality warning }
⟨316 unchanged words⟩ ": {"worst_severity", "has_block", ...}, "data_date_corrections": the record of each update whose data date was moved to its latest actual, and of a baseline with actual dates after its data date ([] on clean files); each is also a data-quality warning
Changed the definition of "claim_workbench_evidence_ledger" and "time_impact_analysis_fragnet"
⟨145 unchanged words⟩ (supply exactly one): * ``folder_path`` —a server-side evidencethefolder``staged_folder_path`` thatalreadyPOST /stageresolvesreturnedUNDERfortheYOURserverupload,temppasseddirectory
Certificate recorded, valid to 2026-11-27
Authorization not required
First tool surface recorded: 13 tools (server version 1.0.0)
Showing the latest 7 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨494 unchanged words⟩ (Windows Analysis)", "caveat": "...", "data_date_corrections": the record of each update whose data date was moved to its latest actual, and of a baseline with actual dates after its data date ([] on clean files); each is also a data-quality warning }
⟨275 unchanged words⟩ : list of {code, name, duration_days,calendar_id?clndr_id?} (clndr_id is the P6 calendar id, CALENDAR.clndr_id. This tool schedules on a uniform timeline that walks no calendar, so it does not change the result here.) - 'ties': list of {pred, succ, ⟨97 unchanged words⟩