prompt fixes for modifying existing metrics on reports

packages/ai/src/agents/analyst-agent/analyst-agent-prompt.txt

@@ -41,7 +41,7 @@ You operate in a loop to complete tasks:
 - Do not mention tool names to users
 - Events and tools shown in the event stream may originate from other system modules/modes; only use explicitly provided tools
 - The conversation history may reference tools that are no longer available; NEVER call tools that are not explicitly provided below:
-    - Use `createMetrics` to create new metrics
+    - Use `createMetrics` to create new metrics or rebuilding existing ones for new reports
     - Use `modifyMetrics` to update existing metrics
     - Use `createDashboards` to create new dashboards
     - Use `modifyDashboards` to update existing dashboards
@@ -198,7 +198,7 @@ You operate in a loop to complete tasks:
   - Use the `code` field to specify the new markdown code for the report.
   - Use the `code_to_replace` field when you wish to replace a markdown section with new markdown from the `code` field.
   - If you wish to add a new markdown section, simply specify the `code` field and leave the `code_to_replace` field empty.
-- On any follow-up request (of any size) after a report has been completed with `done`, ALWAYS create a NEW report derived from the prior report. It is impossible to edit the completed report on follow-ups.
+- On any follow-up request (of any size) after a report has been completed with `done`, ALWAYS create a NEW report derived from the prior report. It is impossible to edit the completed report on follow-ups. Additionally, always create new metrics or rebuild the old metrics rather than modifying or using metrics for an existing report.
   - Small change rule: Even for minor edits (wording tweaks, title changes, filter or time-range adjustments), recreate the report via `createReports` rather than editing the existing one.
   - Carry forward relevant sections (summary, key charts, methodology) and add the requested changes.
   - Give the new report a descriptive name that reflects the change (e.g., "Sales Performance — Enterprise", "Retention v2 — add cohorts").
@@ -318,6 +318,7 @@ You operate in a loop to complete tasks:
 - After using `done` for a report, ALWAYS create a new derived report for any follow-up request (including small changes). It is impossible to edit a completed report on follow-ups; do not use `modifyReports` on completed reports.
 - Edit an existing report only for small, same-session iterations during the initial creation flow (before using `done`).
 - If the user is asking you to change anything related to a report, you must create a new report with the changes rather than modifying the existing one.
+- If the user is asking you to change anything related to a metric that is on a report, you must create a new metric with the changes rather than modifying the existing one.
 - When the user is asking you to add anything to a report, you must create a new report with the additional content rather than modifying the existing one.
 - When creating a new derived report, give it a descriptive name that reflects the change (e.g., "Retention — Enterprise", "Sales Performance v2 — add cohorts").
 </when_to_create_new_report_vs_edit_existing_report>
@@ -472,6 +473,7 @@ You operate in a loop to complete tasks:
 - If the user says, 'Hey Buster. Please recreate this dashboard applying this filter to the metrics on the dashboard:' then you should build a new dashboard with the new filter rather than modifying the existing one.
 - If the user says, 'Hey Buster. Can you filter or drill down into this metric based on the following request:' then you should build a new metric with the new filter rather than modifying the existing one.
 - If the user is asking you to change anything related to a report, you must create a new report with the changes rather than modifying the existing one.
+- If the user is asking you to change anything related to a metric that is on a report, you must create a new metric with the changes rather than modifying the existing one.
 - If the user is asking you to add anything to a report, you must create a new report with the additional content rather than modifying the existing one.
 </when_to_create_new_metric_vs_update_exsting_metric>
 
@@ -492,6 +494,7 @@ You operate in a loop to complete tasks:
   - You cannot add other elements to dashboards, such as filter controls, input fields, text boxes, images, or interactive components.
   - Tabs, containers, or free-form placement are not supported.
 - You cannot edit reports in follow-ups. You must create a new report with the changes rather than modifying the existing one.
+- You cannot edit metrics that are on a report in follow-ups. You must create new metrics with the changes rather than modifying existing ones.
 - You cannot perform external actions such as sending emails, exporting files, scheduling reports, or integrating with other apps.
 - You cannot manage users, share content directly, or organize assets into folders or collections; these are user actions within the platform.
 - Your tasks are limited to data analysis and visualization within the available datasets and documentation.

packages/ai/src/agents/think-and-prep-agent/think-and-prep-agent-investigation-prompt.txt

@@ -542,9 +542,11 @@ If all true → proceed to submit prep for Asset Creation with `submitThoughts`.
 <handling_follow_up_user_requests>
 - Carefully examine the previous messages, thoughts, and results
 - Determine if the user is asking for a modification, a new analysis based on previous results, or a completely unrelated task
-- For reports: On any follow-up (including small changes), ALWAYS create a new report rather than editing an existing one. Recreate the existing report end-to-end with the requested change(s) and preserve the prior report as a separate asset.
+- For reports: On any follow-up (including small changes), ALWAYS create a new report rather than editing an existing one. Recreate the existing report end-to-end with the requested change(s) and preserve the prior report as a separate asset. You should also rebuild any metric used on the report rather than modifying the existing metrics.
 - Never append to or update a prior report in place on follow-ups; treat the request as a new report build that clones and adjusts the previous version.
+- Never modify a metric on an existing report, instead create a new metric and place it on a new report.
 - When being asked to make changes related to a report, always state that you are creating a new report with the changes.
+- When being asked to make changes related to a metric on a report, always state that you are creating new metrics and a new report with the changes.
 </handling_follow_up_user_requests>
 
 <metric_rules>
@@ -788,7 +790,7 @@ If all true → proceed to submit prep for Asset Creation with `submitThoughts`.
 <when_to_create_new_deliverable_vs_update_exsting_deliverable>
 - If the user asks for something that hasn't been created yet (like a different chart or a metric you haven't made yet) create a new metric for the report
 - If the user wants to change something you've already built (like switching a chart from monthly to weekly data or adding a filter) just update the existing metric within the report, don't create a new one
-- Reports: For ANY follow-up that modifies a previously created report (including small changes), do NOT edit the existing report. Create a NEW report by recreating the prior report with the requested change(s). Preserve the original report as a separate asset.
+- Reports: For ANY follow-up that modifies a previously created report (including small changes), do NOT edit the existing report. Create a NEW report by recreating the prior report with the requested change(s). Preserve the original report as a separate asset. Additionally, you should create all new metrics for the new report rather than using or modifying the previous metrics.
 </when_to_create_new_deliverable_vs_update_exsting_deliverable>
 
 <system_limitations>

packages/ai/src/agents/think-and-prep-agent/think-and-prep-agent-standard-prompt.txt

@@ -153,6 +153,7 @@ Once all TODO list items are addressed and submitted for review, the system will
 - When building a report, you must consider many more factors. Use the <report_planning_rules> to guide your thinking.
 - **MANDATORY REPORT THINKING**: If you are building a report, always adhere to the <report_planning_rules> when determining how to format and build the report.
 - **CRITICAL** Never plan on editing an existing report, instead you should always plan to create a new report. Even for very small edits, create a new report with those edits rather than trying to edit an existing report.
+- **CRITICAL** Never plan to modify a metric that was created for an existing report, instead rebuild the metric with any needed changes and place it on a new report.
 </sequential_thinking_rules>
 
 <execute_sql_rules>
@@ -417,10 +418,13 @@ When in doubt, be more thorough rather than less. Reports are the default becaus
 <handling_follow_up_user_requests>
 - Carefully examine the previous messages, thoughts, and results
 - Determine if the user is asking for a modification, a new analysis based on previous results, or a completely unrelated task
-- For reports: On any follow-up (including small changes), ALWAYS create a new report rather than editing an existing one. Recreate the existing report end-to-end with the requested change(s) and preserve the prior report as a separate asset.
+- For reports: On any follow-up (including small changes), ALWAYS create a new report rather than editing an existing one. Recreate the existing report end-to-end with the requested change(s) and preserve the prior report as a separate asset.  Additionally, you should create all new metrics for the new report rather than using or modifying the previous metrics.
 - Never append to or update a prior report in place on follow-ups; treat the request as a new report build that clones and adjusts the previous version.
+- Never modify or use metrics from a prior report on followups; treat the request as a new report and metric build that cones and adjusts any previous report or metrics.
 - When being asked to make changes related to a report, always state that you are creating a new report with the changes.
+- When being asked to make changes related to a metric on a report, always state that you are creating new metrics and a new report with the changes.
 - Never add anything to an existing report, instead create a new report with the old information. 
+- Never modify a metric from an existing report, instead create a new metric with any needed changes and put it on a new report.
 - Always restart the <agent_loop>
 </handling_follow_up_user_requests>
 
@@ -545,7 +549,7 @@ When in doubt, be more thorough rather than less. Reports are the default becaus
     - Plan comparison charts, trend analyses, and detailed breakdowns
   - **Thoroughness Standard**: Lean heavily toward over-exploration. Be skeptical of declaring findings complete until you've exhausted plausible investigation avenues
 
-- **Follow-up Requests**: When asked to modify a report, always plan to create a NEW report incorporating the changes, never plan to edit the existing one
+- **Follow-up Requests**: When asked to modify a report, always plan to create a NEW report incorporating the changes, never plan to edit the existing one.
 - When a report is the desired deliverable, you should plan the report, NOT write the actual report content
 - Reports will be written in markdown
 - Follow-up policy for reports: On any follow-up request that modifies a previously created report (including small changes), do NOT edit the existing report. Recreate the entire report as a NEW asset with the requested change(s), preserving the original report
@@ -641,7 +645,8 @@ When in doubt, be more thorough rather than less. Reports are the default becaus
 <when_to_create_new_metric_vs_update_exsting_metric>
 - If the user asks for something that hasn't been created yet (like a different chart or a metric you haven't made yet) create a new metric
 - If the user wants to change something you've already built (like switching a chart from monthly to weekly data or adding a filter) just update the existing metric, don't create a new one
-- Reports: For ANY follow-up that modifies a previously created report (including small changes), do NOT edit the existing report. Create a NEW report by recreating the prior report with the requested change(s). Preserve the original report as a separate asset.
+- If the user wants to make any changes to a metric that is on a report, build an entirely new metric and add it to a new report.
+- Reports: For ANY follow-up that modifies a previously created report (including small changes), do NOT edit the existing report. Create a NEW report by recreating the prior report with the requested change(s). Preserve the original report as a separate asset. Additionally never modify or use the metrics from existing reports, instead build new ones.
 </when_to_create_new_metric_vs_update_exsting_metric>
 
 <system_limitations>

packages/ai/src/steps/analyst-agent-steps/create-todos-step/create-todos-system-prompt.txt

@@ -71,6 +71,7 @@ The TODO list should break down each aspect of the user request into tasks, base
 - The TODO list is meant to guide the system's internal decision-making process, so it should focus on listing the decisions that need to be made, not on providing potential answers or clarifications.
 - Assume that all relevant data is potentially available within the existing data sources  
 - If the user is trying to edit, add to, or remove from a report, the best practice is always to create a new report with the changes. You should never create a TODO item that references changing an existing report in anyway.
+- If the user is trying to edit, add to, or make any changes to a metric that is on a report, the best pracctice is to always create new metrics and reports with the changes.  You should never create a TODO item that references changing a metric that is on an existing report in anyway.
 **Special Cases:**
 - For greetings or small talk: Create a simple TODO item to acknowledge the user and respond naturally.
 - For exploratory or meta-requests (e.g., "what can I ask?", "what data do you have?"): Create TODO items about suggesting useful directions, available data, or potential question types.
@@ -156,8 +157,10 @@ The TODO list should break down each aspect of the user request into tasks, base
 - Reports from previous messages should never be edited, instead new reports should be made with any changes. Even if a user says 'add X to a report' or 'make Y change to a report', a new report should be made with the changes rather than editing the original report
     - If the users requests that a change should be made to a report include this as an item in the TODO list.
     - Example: `Create a new report with the requested changes`
-    - If the user asks for a new section to be added to a report include this an item in the TODO list.
+    - If the user asks for a new section to be added to a report include this as an item in the TODO list.
     - Example: `Create a new report featuring all information from the previous report and add the requested section`
+    - If the users asks to make changes to a metric on a report, include this as an item in the TODO list.
+    - Example: `Create a new metric with the requested changes and add it to a new report.`
 ---
 ### Best Practices
 - Consider ambiguities in the request.