tool changes

Author: tmelliottjr

pkg/github/instructions.go

@@ -62,79 +62,6 @@ Check 'list_issue_types' first for organizations to use proper issue types. Use
 		return `## Discussions
 		
 Use 'list_discussion_categories' to understand available categories before creating discussions. Filter by category for better organization.`
-	case "projects":
-		return `## Projects
-
-Workflow: 1) list_project_fields (get field IDs), 2) list_project_items (with pagination), 3) optional updates.
-
-Field usage:
-	- Call list_project_fields first to understand available fields and get IDs/types before filtering.
-	- Use EXACT returned field names (case-insensitive match). Don't invent names or IDs.
-	- Iteration synonyms (sprint/cycle) only if that field exists; map to the actual name (e.g. sprint:@current).
-	- Only include filters for fields that exist and are relevant.
-
-Pagination (mandatory):
-	- Loop while pageInfo.hasNextPage=true using after=pageInfo.nextCursor.
-	- Keep query, fields, per_page IDENTICAL on every page.
-	- Use before=pageInfo.prevCursor only when explicitly navigating to a previous page.
-	- Do not analyze until ALL pages fetched.
-
-Counting rules:
-	- Count items array length after full pagination.
-	- If multi-page: collect all pages, dedupe by item.id (fallback node_id) before totals.
-	- Never count field objects, content, or nested arrays as separate items.
-	- item.id = project item ID (for updates/deletes). item.content.id = underlying issue/PR ID.
-
-Summary vs list:
-	- Summaries ONLY if user uses verbs: analyze | summarize | summary | report | overview | insights.
-	- Listing verbs (list/show/get/fetch/display/enumerate) → enumerate + total.
-
-Self-check before returning:
-	- Paginated fully
-	- Dedupe by id/node_id
-	- Correct IDs used
-	- Field names valid
-	- Summary only if requested.
-
-Return COMPLETE data or state what's missing (e.g. pages skipped).
-
-list_project_items query rules:
-Query string - For advanced filtering of project items using GitHub's project filtering syntax:
-
-MUST reflect user intent; strongly prefer explicit content type if narrowed:
-	- "open issues" → state:open is:issue
-	- "merged PRs" → state:merged is:pr
-	- "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 specifies "items")
-	- "list all open P2 issues" → is:issue state:open priority:p2 (include state if user wants open or closed, include type if user specifies "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
-	c. Map negations: "excluding wontfix" → -label:wontfix
-	d. Map priority adjectives: "high/sev1/p1" → priority:high OR priority:p1 (choose based on field presence)
-	e. When filtering by label, always use wildcard matching to account for cross-repository differences or emojis: (e.g. "bug 🐛" → label:*bug*)
-	f. When filtering by milestone, always use wildcard matching to account for cross-repository differences: (e.g. "v1.0" → milestone:*v1.0*)
-
-Syntax Essentials (items):
-   AND: space-separated. (label:bug priority:high).
-   OR: comma inside one qualifier (label:bug,critical).
-   NOT: leading '-' (-label:wontfix).
-   Hyphenate multi-word field names. (team-name:"Backend Team", story-points:>5).
-   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 |
-   priority:p1|high | sprint-name:@current | team-name:"Backend Team" | parent-issue:"org/repo#123" |
-   updated:>@today-7d | title:*text* | -label:wontfix | label:bug,critical | no:assignee | has:label
-
-Never:
-   - Infer field IDs; fetch via list_project_fields.
-   - Drop 'fields' param on subsequent pages if field values are needed.`
 	default:
 		return ""
 	}

pkg/github/projects.go

@@ -1066,186 +1066,3 @@ func addOptions(s string, opts any) (string, error) {
 	origURL.RawQuery = origValues.Encode()
 	return origURL.String(), nil
 }
-
-func ManageProjectItemsPrompt(t translations.TranslationHelperFunc) (tool mcp.Prompt, handler server.PromptHandlerFunc) {
-	return mcp.NewPrompt("ManageProjectItems",
-			mcp.WithPromptDescription(t("PROMPT_MANAGE_PROJECT_ITEMS_DESCRIPTION", "Guide for GitHub Projects V2: discovery, fields, querying, updates.")),
-			mcp.WithArgument("owner", mcp.ArgumentDescription("The owner of the project (user or organization name)"), mcp.RequiredArgument()),
-			mcp.WithArgument("owner_type", mcp.ArgumentDescription("Type of owner: 'user' or 'org'"), mcp.RequiredArgument()),
-		), func(_ context.Context, request mcp.GetPromptRequest) (*mcp.GetPromptResult, error) {
-			owner := request.Params.Arguments["owner"]
-			ownerType := request.Params.Arguments["owner_type"]
-
-			task := ""
-			if t, exists := request.Params.Arguments["task"]; exists {
-				task = fmt.Sprintf("%v", t)
-			}
-
-			messages := []mcp.PromptMessage{
-				{
-					Role: "system",
-					Content: mcp.NewTextContent(`System guide: GitHub Projects V2.
-Goal: Pick correct tool, fetch COMPLETE data (no early pagination stop), apply accurate filters, and count items correctly.
-
-Core rules:
-- 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
-
-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
-
-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
-
-Edge handling:
-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?`),
-				},
-				{
-					Role: "user",
-					Content: mcp.NewTextContent(fmt.Sprintf("I want to work with GitHub Projects for %s (owner_type: %s).%s",
-						owner,
-						ownerType,
-						func() string {
-							if task != "" {
-								return fmt.Sprintf(" Focus: %s.", task)
-							}
-							return ""
-						}())),
-				},
-				{
-					Role:    "assistant",
-					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 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.`),
-				},
-				{
-					Role:    "user",
-					Content: mcp.NewTextContent("How do I update item field values?"),
-				},
-				{
-					Role: "assistant",
-					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 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 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(`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 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{
-				Messages: messages,
-			}, nil
-		}
-}

pkg/github/tools.go

@@ -328,9 +328,7 @@ func DefaultToolsetGroup(readOnly bool, getClient GetClientFn, getGQLClient GetG
 			toolsets.NewServerTool(AddProjectItem(getClient, t)),
 			toolsets.NewServerTool(DeleteProjectItem(getClient, t)),
 			toolsets.NewServerTool(UpdateProjectItem(getClient, t)),
-		).AddPrompts(
-		toolsets.NewServerPrompt(ManageProjectItemsPrompt(t)),
-	)
+		)
 	stargazers := toolsets.NewToolset(ToolsetMetadataStargazers.ID, ToolsetMetadataStargazers.Description).
 		AddReadTools(
 			toolsets.NewServerTool(ListStarredRepositories(getClient, t)),