prompt updates

Author: tmelliottjr

pkg/github/projects.go

@@ -460,6 +460,7 @@ MUST reflect user intent; strongly prefer explicit content type if narrowed:
 	- "items updated this week" → updated:>@today-7d (omit type only if mixed desired)
 	- "list all P1 priority items" → priority:p1 (omit state if user wants all, omit type if user speciifies "items")
 	- "list all open P2 issues" → is:issue state:open priority:p2 (include state if user wants open or closed, include type if user speciifies "issues" or "PRs")
+	- "all open issues I'm working on" → is:issue state:open assignee:@me
 Query Construction Heuristics:
 	a. Extract type nouns: issues → is:issue | PRs, Pulls, or Pull Requests → is:pr | tasks/tickets → is:issue (ask if ambiguity)
 	b. Map temporal phrases: "this week" → updated:>@today-7d
@@ -474,6 +475,7 @@ Syntax Essentials (items):
    Quote multi-word values. (status:"In Review" team-name:"Backend Team").
    Ranges: points:1..3, updated:<@today-30d.
    Wildcards: title:*crash*, label:bug*.
+	 Assigned to User: assignee:@me | assignee:username | no:assignee
 
 Common Qualifier Glossary (items):
    is:issue | is:pr | state:open|closed|merged | assignee:@me|username | label:NAME | status:VALUE |
@@ -1255,40 +1257,52 @@ func ManageProjectItemsPrompt(t translations.TranslationHelperFunc) (tool mcp.Pr
 				{
 					Role: "system",
 					Content: mcp.NewTextContent(`System guide: GitHub Projects V2.
-Goal: Pick correct method, fetch COMPLETE data (no early pagination stop), apply accurate filters, and count items correctly.
+Goal: Pick correct tool, fetch COMPLETE data (no early pagination stop), apply accurate filters, and count items correctly.
 
-Method quick map:
-list_projects (metadata only) | get_project (single) | list_project_fields (define IDs) | get_project_field | list_project_items (issues/PRs) | get_project_item | project_write (mutations) | issue_read / pull_request_read (deep details)
+Available tools (9 total):
+
+Read-only tools:
+- list_projects: List all projects for a user/org
+- get_project: Get details of a single project by project_number
+- list_project_fields: List all fields in a project (CALL THIS FIRST before filtering)
+- get_project_field: Get details of a single field by field_id
+- list_project_items: List items (issues/PRs) in a project with filtering & field values
+- get_project_item: Get a single item by item_id
+
+Write tools:
+- add_project_item: Add an issue or PR to a project
+- update_project_item: Update field values for an item (status, priority, etc.)
+- delete_project_item: Remove an item from a project
 
 Core rules:
-- list_projects: NEVER include item-level filters.
-- Before filtering on custom fields call list_project_fields.
-- Always paginate until pageInfo.hasNextPage=false.
-- Keep query, fields, per_page identical across pages.
-- Include fields IDs on every list_project_items page if you need values.
-- Prefer explicit is:issue / is:pr unless mixed set requested.
-- Only summarize if verbs like analyze / summarize / report / overview / insights appear; otherwise enumerate.
+- list_projects: NEVER include item-level filters (no is:issue, assignee:, label:, etc.)
+- Before filtering on fields, call list_project_fields to get field IDs
+- Always paginate until pageInfo.hasNextPage=false
+- Keep query, fields, per_page identical across pages
+- Include field IDs on every list_project_items page if you need values
+- Prefer explicit is:issue / is:pr unless mixed set requested
+- Only summarize if verbs like analyze / summarize / report / overview / insights appear; otherwise enumerate
 
 Field resolution:
-- Use exact returned field names; don't invent.
-- Iteration synonyms map to actual existing name (Sprint → sprint:@current, etc.). If none exist, omit.
-- Only add filters for fields that exist and matter to the user goal.
+- Use exact returned field names; don't invent
+- Iteration synonyms map to actual existing name (Sprint → sprint:@current, etc.). If none exist, omit
+- Only add filters for fields that exist and matter to the user goal
 
 Query syntax essentials:
 AND space | OR comma | NOT prefix - | quote multi-word values | hyphenate names | ranges points:1..5 | comparisons updated:>@today-7d priority:>1 | wildcards title:*crash*
 
 Pagination pattern:
-Call list_project_items → if hasNextPage true, repeat with after=nextCursor → stop only when false → then count/deduplicate.
+Call list_project_items → if hasNextPage true, repeat with after=nextCursor → stop only when false → then count/deduplicate
 
 Counting:
-- Items array length after full pagination (dedupe by item.id or node_id).
-- Never count fields array, content, assignees, labels as separate items.
-- item.id = project item identifier; content.id = underlying issue/PR id.
+- Items array length after full pagination (dedupe by item.id or node_id)
+- Never count fields array, content, assignees, labels as separate items
+- item.id = project item identifier; content.id = underlying issue/PR id
 
 Edge handling:
-Empty pages → total=0 still return pageInfo.
-Duplicates → keep first for totals.
-Missing field values → null/omit, never fabricate.
+Empty pages → total=0 still return pageInfo
+Duplicates → keep first for totals
+Missing field values → null/omit, never fabricate
 
 Self-check: paginated? deduped? correct IDs? field names valid? summary allowed?`),
 				},
@@ -1306,22 +1320,23 @@ Self-check: paginated? deduped? correct IDs? field names valid? summary allowed?
 				},
 				{
 					Role:    "assistant",
-					Content: mcp.NewTextContent("Start by listing projects: project_read method=\"list_projects\"."),
+					Content: mcp.NewTextContent("Start by listing projects: use list_projects tool with owner and owner_type parameters."),
 				},
 				{
 					Role:    "user",
 					Content: mcp.NewTextContent("How do I work with fields and items?"),
 				},
 				{
 					Role: "assistant",
-					Content: mcp.NewTextContent(`Fields & items:
-1. list_project_fields first → map lowercased name -> {id,type}.
-2. Use only existing field names; no invention.
-3. Iteration mapping: pick sprint/cycle/iteration only if present (sprint:@current etc.).
-4. Include only relevant fields (e.g. Priority + Label for high priority bugs).
-5. Build query after resolving fields ("last week" → updated:>@today-7d).
-6. Paginate until hasNextPage=false; keep query/fields/per_page stable.
-7. Include fields IDs every page when you need their values.
+					Content: mcp.NewTextContent(`Fields & items workflow:
+1. Call list_project_fields to get field definitions → map lowercased name -> {id,type}
+2. Use only existing field names; no invention
+3. Iteration mapping: pick sprint/cycle/iteration only if present (sprint:@current etc.)
+4. Include only relevant fields (e.g. Priority + Label for high priority bugs)
+5. Build query after resolving fields ("last week" → updated:>@today-7d)
+6. Call list_project_items with query and field IDs → paginate until hasNextPage=false
+7. Keep query/fields/per_page stable across all pages
+8. Include field IDs on every page when you need their values
 Missing field? Omit or clarify—never guess.`),
 				},
 				{
@@ -1330,58 +1345,90 @@ Missing field? Omit or clarify—never guess.`),
 				},
 				{
 					Role: "assistant",
-					Content: mcp.NewTextContent(`Updating fields (project_write update_project_item):
-Examples: text {"id":123,"value":"hello"} | select {"id":456,"value":789} (option ID) | number {"id":321,"value":5} | date {"id":654,"value":"2025-03-15"} | clear {"id":123,"value":null}
-Rules: item_id = project item wrapper ID; confirm field IDs via list_project_fields; select/iteration = pass option/iteration ID (not name).`),
+					Content: mcp.NewTextContent(`Updating fields (update_project_item tool):
+Input format: updated_field parameter with {id: <field_id>, value: <new_value>}
+Examples:
+- Text field: {"id":123,"value":"hello"}
+- Single-select: {"id":456,"value":789} (value is option ID, not name)
+- Number: {"id":321,"value":5}
+- Date: {"id":654,"value":"2025-03-15"}
+- Clear field: {"id":123,"value":null}
+
+Rules:
+- item_id parameter = project item ID (from list_project_items), NOT issue/PR ID
+- Get field IDs from list_project_fields first
+- For select/iteration fields, pass option/iteration ID as value, not the name
+- To add an item first: use add_project_item tool with issue/PR ID
+- To remove an item: use delete_project_item tool`),
 				},
 				{
 					Role:    "user",
 					Content: mcp.NewTextContent("Show me a workflow example."),
 				},
 				{
 					Role: "assistant",
-					Content: mcp.NewTextContent(`Workflow quick path:
-1 list_projects → pick project_number.
-2 list_project_fields → build field map.
-3 Build query (e.g. is:issue sprint:@current priority:high updated:>@today-7d).
-4 list_project_items (include field IDs) → paginate fully.
-5 Optional deep dive: issue_read / pull_request_read per item.
-6 Optional update: project_write update_project_item.
-Reminders: iteration filter must match existing field; keep fields consistent; summarize only if asked.`),
+					Content: mcp.NewTextContent(`Workflow example:
+1. list_projects → pick project_number
+2. list_project_fields → build field map {name: {id, type}}
+3. Build query (e.g. is:issue sprint:@current priority:high updated:>@today-7d)
+4. list_project_items with field IDs → paginate fully (loop until hasNextPage=false)
+5. Optional: get_project_item for specific item details
+6. Optional: add_project_item to add issue/PR to project
+7. Optional: update_project_item to change field values for an item
+8. Optional: delete_project_item to remove from an item from project
+
+Important:
+- Iteration filter must match existing field name
+- Keep fields parameter consistent across pages
+- Summarize only if explicitly asked
+- item_id for updates/deletes comes from list_project_items response
+- content.id in items is the underlying issue/PR ID (use with add_project_item)`),
 				},
 				{
 					Role:    "user",
 					Content: mcp.NewTextContent("How do I handle pagination?"),
 				},
 				{
 					Role: "assistant",
-					Content: mcp.NewTextContent(`Pagination:
-Loop while hasNextPage=true using after=nextCursor.
-Do NOT change query/fields/per_page.
-Include same fields IDs every page.
-Only count/summarize after final page.`),
+					Content: mcp.NewTextContent(`Pagination with list_project_items:
+1. Make initial call with query, fields, per_page parameters
+2. Check response pageInfo.hasNextPage
+3. If true: call again with same query/fields/per_page + after=pageInfo.nextCursor
+4. Repeat step 2-3 until hasNextPage=false
+5. Collect all items from all pages before counting/analyzing
+
+Critical: Do NOT change query, fields, or per_page between pages. Always include same field IDs on every page if you need field values.`),
 				},
 				{
 					Role:    "user",
 					Content: mcp.NewTextContent("How do I get more details about items?"),
 				},
 				{
 					Role: "assistant",
-					Content: mcp.NewTextContent(`Deep details:
-Use issue_read or pull_request_read for comments/reviews/diffs after enumeration.
-Inputs: repository + item content.number.
-Confirm type (is:issue vs is:pr) before choosing which tool.`),
+					Content: mcp.NewTextContent(`Getting additional item details:
+
+- First inspect item's content object for info, e.g. title, assignees, labels
+- If additional detail is needed, and relevant fields are present from list_project_fields, include their IDs in list_project_items and request with list_project_items again.
+- If more detail needed, use separate issue/PR tools`),
 				},
 				{
 					Role: "assistant",
-					Content: mcp.NewTextContent(`Query patterns:
-blocked issues → is:issue (label:blocked OR status:"Blocked")
-overdue tasks → is:issue due-date:<@today state:open
-PRs ready for review → is:pr review-status:"Ready for Review" state:open
-stale issues → is:issue updated:<@today-30d state:open
-high priority bugs → is:issue label:bug priority:high state:open
-team sprint PRs → is:pr team-name:"Backend Team" sprint:@current
-Rules: summarize only if asked; dedupe before counts; quote multi-word values; never invent field names or IDs.`),
+					Content: mcp.NewTextContent(`Query patterns for list_project_items:
+
+Common scenarios:
+- Blocked issues: is:issue (label:blocked OR status:"Blocked")
+- Overdue tasks: is:issue due-date:<@today state:open
+- PRs ready for review: is:pr review-status:"Ready for Review" state:open
+- Stale issues: is:issue updated:<@today-30d state:open
+- High priority bugs: is:issue label:bug priority:high state:open
+- Team sprint PRs: is:pr team-name:"Backend Team" sprint:@current
+
+Rules:
+- Summarize only if user requests it with verbs like "analyze", "summarize", "report"
+- Deduplicate by item.id before counting totals
+- Quote multi-word values: status:"In Progress"
+- Never invent field names or IDs - always verify with list_project_fields first
+- Use explicit is:issue or is:pr unless user wants mixed items`),
 				},
 			}
 			return &mcp.GetPromptResult{